Manipuri-NLP

A comprehensive overview of research regarding Natural Language Processing (NLP) of Manipuri language.
https://github.com/galax19ksh/Manipuri-NLP

Last synced: about 23 hours ago
JSON representation

RMWE
- Sentiment Analysis
  - Low resource language specific pre-processing and features for sentiment analysis task - specific preprocessing tasks and reporting improved classification results in terms of precision, recall, and F-score, particularly with ensemble voting of the top three classifiers based on TF-IDF, along with findings from deep learning-based methods. |
  - Review Comments of Manipuri Online Video: Good, Bad or Ugly - based approaches, on a resource-constrained dataset of Manipuri comments from social media platforms, emphasizing the significance of pre-processing and feature engineering. |
  - Low resource language specific pre-processing and features for sentiment analysis task - specific preprocessing tasks and reporting improved classification results in terms of precision, recall, and F-score, particularly with ensemble voting of the top three classifiers based on TF-IDF, along with findings from deep learning-based methods. |
  - Review Comments of Manipuri Online Video: Good, Bad or Ugly - based approaches, on a resource-constrained dataset of Manipuri comments from social media platforms, emphasizing the significance of pre-processing and feature engineering. |
  - Low resource language specific pre-processing and features for sentiment analysis task - specific preprocessing tasks and reporting improved classification results in terms of precision, recall, and F-score, particularly with ensemble voting of the top three classifiers based on TF-IDF, along with findings from deep learning-based methods. |
  - Review Comments of Manipuri Online Video: Good, Bad or Ugly - based approaches, on a resource-constrained dataset of Manipuri comments from social media platforms, emphasizing the significance of pre-processing and feature engineering. |
  - Review Comments of Manipuri Online Video: Good, Bad or Ugly - based approaches, on a resource-constrained dataset of Manipuri comments from social media platforms, emphasizing the significance of pre-processing and feature engineering. |
  - Low resource language specific pre-processing and features for sentiment analysis task - specific preprocessing tasks and reporting improved classification results in terms of precision, recall, and F-score, particularly with ensemble voting of the top three classifiers based on TF-IDF, along with findings from deep learning-based methods. |
  - Review Comments of Manipuri Online Video: Good, Bad or Ugly - based approaches, on a resource-constrained dataset of Manipuri comments from social media platforms, emphasizing the significance of pre-processing and feature engineering. |
  - Low resource language specific pre-processing and features for sentiment analysis task - specific preprocessing tasks and reporting improved classification results in terms of precision, recall, and F-score, particularly with ensemble voting of the top three classifiers based on TF-IDF, along with findings from deep learning-based methods. |
  - Review Comments of Manipuri Online Video: Good, Bad or Ugly - based approaches, on a resource-constrained dataset of Manipuri comments from social media platforms, emphasizing the significance of pre-processing and feature engineering. |
  - Review Comments of Manipuri Online Video: Good, Bad or Ugly - based approaches, on a resource-constrained dataset of Manipuri comments from social media platforms, emphasizing the significance of pre-processing and feature engineering. |
  - Low resource language specific pre-processing and features for sentiment analysis task - specific preprocessing tasks and reporting improved classification results in terms of precision, recall, and F-score, particularly with ensemble voting of the top three classifiers based on TF-IDF, along with findings from deep learning-based methods. |
  - Review Comments of Manipuri Online Video: Good, Bad or Ugly - based approaches, on a resource-constrained dataset of Manipuri comments from social media platforms, emphasizing the significance of pre-processing and feature engineering. |
  - Review Comments of Manipuri Online Video: Good, Bad or Ugly - based approaches, on a resource-constrained dataset of Manipuri comments from social media platforms, emphasizing the significance of pre-processing and feature engineering. |
  - Low resource language specific pre-processing and features for sentiment analysis task - specific preprocessing tasks and reporting improved classification results in terms of precision, recall, and F-score, particularly with ensemble voting of the top three classifiers based on TF-IDF, along with findings from deep learning-based methods. |
  - Review Comments of Manipuri Online Video: Good, Bad or Ugly - based approaches, on a resource-constrained dataset of Manipuri comments from social media platforms, emphasizing the significance of pre-processing and feature engineering. |
  - Low resource language specific pre-processing and features for sentiment analysis task - specific preprocessing tasks and reporting improved classification results in terms of precision, recall, and F-score, particularly with ensemble voting of the top three classifiers based on TF-IDF, along with findings from deep learning-based methods. |
  - Review Comments of Manipuri Online Video: Good, Bad or Ugly - based approaches, on a resource-constrained dataset of Manipuri comments from social media platforms, emphasizing the significance of pre-processing and feature engineering. |
  - Low resource language specific pre-processing and features for sentiment analysis task - specific preprocessing tasks and reporting improved classification results in terms of precision, recall, and F-score, particularly with ensemble voting of the top three classifiers based on TF-IDF, along with findings from deep learning-based methods. |
  - Review Comments of Manipuri Online Video: Good, Bad or Ugly - based approaches, on a resource-constrained dataset of Manipuri comments from social media platforms, emphasizing the significance of pre-processing and feature engineering. |
  - Low resource language specific pre-processing and features for sentiment analysis task - specific preprocessing tasks and reporting improved classification results in terms of precision, recall, and F-score, particularly with ensemble voting of the top three classifiers based on TF-IDF, along with findings from deep learning-based methods. |
  - Review Comments of Manipuri Online Video: Good, Bad or Ugly - based approaches, on a resource-constrained dataset of Manipuri comments from social media platforms, emphasizing the significance of pre-processing and feature engineering. |
  - Low resource language specific pre-processing and features for sentiment analysis task - specific preprocessing tasks and reporting improved classification results in terms of precision, recall, and F-score, particularly with ensemble voting of the top three classifiers based on TF-IDF, along with findings from deep learning-based methods. |
  - Review Comments of Manipuri Online Video: Good, Bad or Ugly - based approaches, on a resource-constrained dataset of Manipuri comments from social media platforms, emphasizing the significance of pre-processing and feature engineering. |
  - Review Comments of Manipuri Online Video: Good, Bad or Ugly - based approaches, on a resource-constrained dataset of Manipuri comments from social media platforms, emphasizing the significance of pre-processing and feature engineering. |
  - Low resource language specific pre-processing and features for sentiment analysis task - specific preprocessing tasks and reporting improved classification results in terms of precision, recall, and F-score, particularly with ensemble voting of the top three classifiers based on TF-IDF, along with findings from deep learning-based methods. |
  - Review Comments of Manipuri Online Video: Good, Bad or Ugly - based approaches, on a resource-constrained dataset of Manipuri comments from social media platforms, emphasizing the significance of pre-processing and feature engineering. |
  - Review Comments of Manipuri Online Video: Good, Bad or Ugly - based approaches, on a resource-constrained dataset of Manipuri comments from social media platforms, emphasizing the significance of pre-processing and feature engineering. |
  - Low resource language specific pre-processing and features for sentiment analysis task - specific preprocessing tasks and reporting improved classification results in terms of precision, recall, and F-score, particularly with ensemble voting of the top three classifiers based on TF-IDF, along with findings from deep learning-based methods. |
  - Review Comments of Manipuri Online Video: Good, Bad or Ugly - based approaches, on a resource-constrained dataset of Manipuri comments from social media platforms, emphasizing the significance of pre-processing and feature engineering. |
  - Low resource language specific pre-processing and features for sentiment analysis task - specific preprocessing tasks and reporting improved classification results in terms of precision, recall, and F-score, particularly with ensemble voting of the top three classifiers based on TF-IDF, along with findings from deep learning-based methods. |
  - Review Comments of Manipuri Online Video: Good, Bad or Ugly - based approaches, on a resource-constrained dataset of Manipuri comments from social media platforms, emphasizing the significance of pre-processing and feature engineering. |
  - Review Comments of Manipuri Online Video: Good, Bad or Ugly - based approaches, on a resource-constrained dataset of Manipuri comments from social media platforms, emphasizing the significance of pre-processing and feature engineering. |
  - Low resource language specific pre-processing and features for sentiment analysis task - specific preprocessing tasks and reporting improved classification results in terms of precision, recall, and F-score, particularly with ensemble voting of the top three classifiers based on TF-IDF, along with findings from deep learning-based methods. |
  - Review Comments of Manipuri Online Video: Good, Bad or Ugly - based approaches, on a resource-constrained dataset of Manipuri comments from social media platforms, emphasizing the significance of pre-processing and feature engineering. |
  - Low resource language specific pre-processing and features for sentiment analysis task - specific preprocessing tasks and reporting improved classification results in terms of precision, recall, and F-score, particularly with ensemble voting of the top three classifiers based on TF-IDF, along with findings from deep learning-based methods. |
  - Review Comments of Manipuri Online Video: Good, Bad or Ugly - based approaches, on a resource-constrained dataset of Manipuri comments from social media platforms, emphasizing the significance of pre-processing and feature engineering. |
  - Low resource language specific pre-processing and features for sentiment analysis task - specific preprocessing tasks and reporting improved classification results in terms of precision, recall, and F-score, particularly with ensemble voting of the top three classifiers based on TF-IDF, along with findings from deep learning-based methods. |
  - Review Comments of Manipuri Online Video: Good, Bad or Ugly - based approaches, on a resource-constrained dataset of Manipuri comments from social media platforms, emphasizing the significance of pre-processing and feature engineering. |
  - Low resource language specific pre-processing and features for sentiment analysis task - specific preprocessing tasks and reporting improved classification results in terms of precision, recall, and F-score, particularly with ensemble voting of the top three classifiers based on TF-IDF, along with findings from deep learning-based methods. |
  - Review Comments of Manipuri Online Video: Good, Bad or Ugly - based approaches, on a resource-constrained dataset of Manipuri comments from social media platforms, emphasizing the significance of pre-processing and feature engineering. |
  - Low resource language specific pre-processing and features for sentiment analysis task - specific preprocessing tasks and reporting improved classification results in terms of precision, recall, and F-score, particularly with ensemble voting of the top three classifiers based on TF-IDF, along with findings from deep learning-based methods. |
  - Review Comments of Manipuri Online Video: Good, Bad or Ugly - based approaches, on a resource-constrained dataset of Manipuri comments from social media platforms, emphasizing the significance of pre-processing and feature engineering. |
  - Low resource language specific pre-processing and features for sentiment analysis task - specific preprocessing tasks and reporting improved classification results in terms of precision, recall, and F-score, particularly with ensemble voting of the top three classifiers based on TF-IDF, along with findings from deep learning-based methods. |
  - Review Comments of Manipuri Online Video: Good, Bad or Ugly - based approaches, on a resource-constrained dataset of Manipuri comments from social media platforms, emphasizing the significance of pre-processing and feature engineering. |
  - Review Comments of Manipuri Online Video: Good, Bad or Ugly - based approaches, on a resource-constrained dataset of Manipuri comments from social media platforms, emphasizing the significance of pre-processing and feature engineering. |
  - Low resource language specific pre-processing and features for sentiment analysis task - specific preprocessing tasks and reporting improved classification results in terms of precision, recall, and F-score, particularly with ensemble voting of the top three classifiers based on TF-IDF, along with findings from deep learning-based methods. |
  - Review Comments of Manipuri Online Video: Good, Bad or Ugly - based approaches, on a resource-constrained dataset of Manipuri comments from social media platforms, emphasizing the significance of pre-processing and feature engineering. |
  - Low resource language specific pre-processing and features for sentiment analysis task - specific preprocessing tasks and reporting improved classification results in terms of precision, recall, and F-score, particularly with ensemble voting of the top three classifiers based on TF-IDF, along with findings from deep learning-based methods. |
  - Review Comments of Manipuri Online Video: Good, Bad or Ugly - based approaches, on a resource-constrained dataset of Manipuri comments from social media platforms, emphasizing the significance of pre-processing and feature engineering. |
  - Review Comments of Manipuri Online Video: Good, Bad or Ugly - based approaches, on a resource-constrained dataset of Manipuri comments from social media platforms, emphasizing the significance of pre-processing and feature engineering. |
  - Review Comments of Manipuri Online Video: Good, Bad or Ugly - based approaches, on a resource-constrained dataset of Manipuri comments from social media platforms, emphasizing the significance of pre-processing and feature engineering. |
  - Low resource language specific pre-processing and features for sentiment analysis task - specific preprocessing tasks and reporting improved classification results in terms of precision, recall, and F-score, particularly with ensemble voting of the top three classifiers based on TF-IDF, along with findings from deep learning-based methods. |
  - Review Comments of Manipuri Online Video: Good, Bad or Ugly - based approaches, on a resource-constrained dataset of Manipuri comments from social media platforms, emphasizing the significance of pre-processing and feature engineering. |
  - Low resource language specific pre-processing and features for sentiment analysis task - specific preprocessing tasks and reporting improved classification results in terms of precision, recall, and F-score, particularly with ensemble voting of the top three classifiers based on TF-IDF, along with findings from deep learning-based methods. |
  - Review Comments of Manipuri Online Video: Good, Bad or Ugly - based approaches, on a resource-constrained dataset of Manipuri comments from social media platforms, emphasizing the significance of pre-processing and feature engineering. |
  - Review Comments of Manipuri Online Video: Good, Bad or Ugly - based approaches, on a resource-constrained dataset of Manipuri comments from social media platforms, emphasizing the significance of pre-processing and feature engineering. |
  - Review Comments of Manipuri Online Video: Good, Bad or Ugly - based approaches, on a resource-constrained dataset of Manipuri comments from social media platforms, emphasizing the significance of pre-processing and feature engineering. |
  - Review Comments of Manipuri Online Video: Good, Bad or Ugly - based approaches, on a resource-constrained dataset of Manipuri comments from social media platforms, emphasizing the significance of pre-processing and feature engineering. |
  - A Study and Analysis of Opinion Mining Research in Indo-Aryan, Dravidian and Tibeto-Burman Language Families
  - Review Comments of Manipuri Online Video: Good, Bad or Ugly - based approaches, on a resource-constrained dataset of Manipuri comments from social media platforms, emphasizing the significance of pre-processing and feature engineering. |
  - Verb Based Manipuri Sentiment Analysis - measure of 75.00\%. |
  - A Study and Analysis of Opinion Mining Research in Indo-Aryan, Dravidian and Tibeto-Burman Language Families
  - Low resource language specific pre-processing and features for sentiment analysis task - specific preprocessing tasks and reporting improved classification results in terms of precision, recall, and F-score, particularly with ensemble voting of the top three classifiers based on TF-IDF, along with findings from deep learning-based methods. |
  - Review Comments of Manipuri Online Video: Good, Bad or Ugly - based approaches, on a resource-constrained dataset of Manipuri comments from social media platforms, emphasizing the significance of pre-processing and feature engineering. |
  - Review Comments of Manipuri Online Video: Good, Bad or Ugly - based approaches, on a resource-constrained dataset of Manipuri comments from social media platforms, emphasizing the significance of pre-processing and feature engineering. |
  - Low resource language specific pre-processing and features for sentiment analysis task - specific preprocessing tasks and reporting improved classification results in terms of precision, recall, and F-score, particularly with ensemble voting of the top three classifiers based on TF-IDF, along with findings from deep learning-based methods. |
  - Review Comments of Manipuri Online Video: Good, Bad or Ugly - based approaches, on a resource-constrained dataset of Manipuri comments from social media platforms, emphasizing the significance of pre-processing and feature engineering. |
  - Review Comments of Manipuri Online Video: Good, Bad or Ugly - based approaches, on a resource-constrained dataset of Manipuri comments from social media platforms, emphasizing the significance of pre-processing and feature engineering. |
  - Low resource language specific pre-processing and features for sentiment analysis task - specific preprocessing tasks and reporting improved classification results in terms of precision, recall, and F-score, particularly with ensemble voting of the top three classifiers based on TF-IDF, along with findings from deep learning-based methods. |
  - Review Comments of Manipuri Online Video: Good, Bad or Ugly - based approaches, on a resource-constrained dataset of Manipuri comments from social media platforms, emphasizing the significance of pre-processing and feature engineering. |
  - Review Comments of Manipuri Online Video: Good, Bad or Ugly - based approaches, on a resource-constrained dataset of Manipuri comments from social media platforms, emphasizing the significance of pre-processing and feature engineering. |
  - Low resource language specific pre-processing and features for sentiment analysis task - specific preprocessing tasks and reporting improved classification results in terms of precision, recall, and F-score, particularly with ensemble voting of the top three classifiers based on TF-IDF, along with findings from deep learning-based methods. |
  - Review Comments of Manipuri Online Video: Good, Bad or Ugly - based approaches, on a resource-constrained dataset of Manipuri comments from social media platforms, emphasizing the significance of pre-processing and feature engineering. |
  - Low resource language specific pre-processing and features for sentiment analysis task - specific preprocessing tasks and reporting improved classification results in terms of precision, recall, and F-score, particularly with ensemble voting of the top three classifiers based on TF-IDF, along with findings from deep learning-based methods. |
  - Review Comments of Manipuri Online Video: Good, Bad or Ugly - based approaches, on a resource-constrained dataset of Manipuri comments from social media platforms, emphasizing the significance of pre-processing and feature engineering. |
  - Review Comments of Manipuri Online Video: Good, Bad or Ugly - based approaches, on a resource-constrained dataset of Manipuri comments from social media platforms, emphasizing the significance of pre-processing and feature engineering. |
  - Low resource language specific pre-processing and features for sentiment analysis task - specific preprocessing tasks and reporting improved classification results in terms of precision, recall, and F-score, particularly with ensemble voting of the top three classifiers based on TF-IDF, along with findings from deep learning-based methods. |
  - Low resource language specific pre-processing and features for sentiment analysis task - specific preprocessing tasks and reporting improved classification results in terms of precision, recall, and F-score, particularly with ensemble voting of the top three classifiers based on TF-IDF, along with findings from deep learning-based methods. |
  - Review Comments of Manipuri Online Video: Good, Bad or Ugly - based approaches, on a resource-constrained dataset of Manipuri comments from social media platforms, emphasizing the significance of pre-processing and feature engineering. |
  - Review Comments of Manipuri Online Video: Good, Bad or Ugly - based approaches, on a resource-constrained dataset of Manipuri comments from social media platforms, emphasizing the significance of pre-processing and feature engineering. |
  - Review Comments of Manipuri Online Video: Good, Bad or Ugly - based approaches, on a resource-constrained dataset of Manipuri comments from social media platforms, emphasizing the significance of pre-processing and feature engineering. |
  - Low resource language specific pre-processing and features for sentiment analysis task - specific preprocessing tasks and reporting improved classification results in terms of precision, recall, and F-score, particularly with ensemble voting of the top three classifiers based on TF-IDF, along with findings from deep learning-based methods. |
  - Review Comments of Manipuri Online Video: Good, Bad or Ugly - based approaches, on a resource-constrained dataset of Manipuri comments from social media platforms, emphasizing the significance of pre-processing and feature engineering. |
  - Low resource language specific pre-processing and features for sentiment analysis task - specific preprocessing tasks and reporting improved classification results in terms of precision, recall, and F-score, particularly with ensemble voting of the top three classifiers based on TF-IDF, along with findings from deep learning-based methods. |
  - Review Comments of Manipuri Online Video: Good, Bad or Ugly - based approaches, on a resource-constrained dataset of Manipuri comments from social media platforms, emphasizing the significance of pre-processing and feature engineering. |
  - Review Comments of Manipuri Online Video: Good, Bad or Ugly - based approaches, on a resource-constrained dataset of Manipuri comments from social media platforms, emphasizing the significance of pre-processing and feature engineering. |
  - Low resource language specific pre-processing and features for sentiment analysis task - specific preprocessing tasks and reporting improved classification results in terms of precision, recall, and F-score, particularly with ensemble voting of the top three classifiers based on TF-IDF, along with findings from deep learning-based methods. |
  - Low resource language specific pre-processing and features for sentiment analysis task - specific preprocessing tasks and reporting improved classification results in terms of precision, recall, and F-score, particularly with ensemble voting of the top three classifiers based on TF-IDF, along with findings from deep learning-based methods. |
  - Review Comments of Manipuri Online Video: Good, Bad or Ugly - based approaches, on a resource-constrained dataset of Manipuri comments from social media platforms, emphasizing the significance of pre-processing and feature engineering. |
  - Review Comments of Manipuri Online Video: Good, Bad or Ugly - based approaches, on a resource-constrained dataset of Manipuri comments from social media platforms, emphasizing the significance of pre-processing and feature engineering. |
  - Low resource language specific pre-processing and features for sentiment analysis task - specific preprocessing tasks and reporting improved classification results in terms of precision, recall, and F-score, particularly with ensemble voting of the top three classifiers based on TF-IDF, along with findings from deep learning-based methods. |
  - Low resource language specific pre-processing and features for sentiment analysis task - specific preprocessing tasks and reporting improved classification results in terms of precision, recall, and F-score, particularly with ensemble voting of the top three classifiers based on TF-IDF, along with findings from deep learning-based methods. |
  - Low resource language specific pre-processing and features for sentiment analysis task - specific preprocessing tasks and reporting improved classification results in terms of precision, recall, and F-score, particularly with ensemble voting of the top three classifiers based on TF-IDF, along with findings from deep learning-based methods. |
  - Review Comments of Manipuri Online Video: Good, Bad or Ugly - based approaches, on a resource-constrained dataset of Manipuri comments from social media platforms, emphasizing the significance of pre-processing and feature engineering. |
  - Review Comments of Manipuri Online Video: Good, Bad or Ugly - based approaches, on a resource-constrained dataset of Manipuri comments from social media platforms, emphasizing the significance of pre-processing and feature engineering. |
  - Review Comments of Manipuri Online Video: Good, Bad or Ugly - based approaches, on a resource-constrained dataset of Manipuri comments from social media platforms, emphasizing the significance of pre-processing and feature engineering. |
  - Low resource language specific pre-processing and features for sentiment analysis task - specific preprocessing tasks and reporting improved classification results in terms of precision, recall, and F-score, particularly with ensemble voting of the top three classifiers based on TF-IDF, along with findings from deep learning-based methods. |
  - Review Comments of Manipuri Online Video: Good, Bad or Ugly - based approaches, on a resource-constrained dataset of Manipuri comments from social media platforms, emphasizing the significance of pre-processing and feature engineering. |
  - Low resource language specific pre-processing and features for sentiment analysis task - specific preprocessing tasks and reporting improved classification results in terms of precision, recall, and F-score, particularly with ensemble voting of the top three classifiers based on TF-IDF, along with findings from deep learning-based methods. |
  - Review Comments of Manipuri Online Video: Good, Bad or Ugly - based approaches, on a resource-constrained dataset of Manipuri comments from social media platforms, emphasizing the significance of pre-processing and feature engineering. |
  - Low resource language specific pre-processing and features for sentiment analysis task - specific preprocessing tasks and reporting improved classification results in terms of precision, recall, and F-score, particularly with ensemble voting of the top three classifiers based on TF-IDF, along with findings from deep learning-based methods. |
  - Review Comments of Manipuri Online Video: Good, Bad or Ugly - based approaches, on a resource-constrained dataset of Manipuri comments from social media platforms, emphasizing the significance of pre-processing and feature engineering. |
  - Low resource language specific pre-processing and features for sentiment analysis task - specific preprocessing tasks and reporting improved classification results in terms of precision, recall, and F-score, particularly with ensemble voting of the top three classifiers based on TF-IDF, along with findings from deep learning-based methods. |
  - Review Comments of Manipuri Online Video: Good, Bad or Ugly - based approaches, on a resource-constrained dataset of Manipuri comments from social media platforms, emphasizing the significance of pre-processing and feature engineering. |
- Speech Technologies
  - Vowel-Based Acoustic and Prosodic Study of Three Manipuri Dialects
  - Vowel-Based Acoustic and Prosodic Study of Three Manipuri Dialects
  - Vowel-Based Acoustic and Prosodic Study of Three Manipuri Dialects
  - Vowel-Based Acoustic and Prosodic Study of Three Manipuri Dialects
  - Vowel-Based Acoustic and Prosodic Study of Three Manipuri Dialects
  - Vowel-Based Acoustic and Prosodic Study of Three Manipuri Dialects
  - Vowel-Based Acoustic and Prosodic Study of Three Manipuri Dialects
  - Vowel-Based Acoustic and Prosodic Study of Three Manipuri Dialects
  - Vowel-Based Acoustic and Prosodic Study of Three Manipuri Dialects
  - Vowel-Based Acoustic and Prosodic Study of Three Manipuri Dialects
  - Vowel-Based Acoustic and Prosodic Study of Three Manipuri Dialects
  - Vowel-Based Acoustic and Prosodic Study of Three Manipuri Dialects
  - Vowel-Based Acoustic and Prosodic Study of Three Manipuri Dialects
  - Vowel-Based Acoustic and Prosodic Study of Three Manipuri Dialects
  - Vowel-Based Acoustic and Prosodic Study of Three Manipuri Dialects
  - Vowel-Based Acoustic and Prosodic Study of Three Manipuri Dialects
  - Vowel-Based Acoustic and Prosodic Study of Three Manipuri Dialects
  - Vowel-Based Acoustic and Prosodic Study of Three Manipuri Dialects
  - Vowel-Based Acoustic and Prosodic Study of Three Manipuri Dialects
  - Vowel-Based Acoustic and Prosodic Study of Three Manipuri Dialects
  - Vowel-Based Acoustic and Prosodic Study of Three Manipuri Dialects
  - Vowel-Based Acoustic and Prosodic Study of Three Manipuri Dialects
  - Vowel-Based Acoustic and Prosodic Study of Three Manipuri Dialects
  - Vowel-Based Acoustic and Prosodic Study of Three Manipuri Dialects
  - Vowel-Based Acoustic and Prosodic Study of Three Manipuri Dialects
  - Vowel-Based Acoustic and Prosodic Study of Three Manipuri Dialects
  - Vowel-Based Acoustic and Prosodic Study of Three Manipuri Dialects
  - MECOS: A bilingual Manipuri–English spontaneous code-switching speech corpus for automatic speech recognition - switched speech database for Manipuri–English, comprising 57 hours of annotated spontaneous speech, aiming to construct an automatic speech recognition (ASR) system, with evaluations revealing the superior performance of the pure TDNN model. |
  - Vowel-Based Acoustic and Prosodic Study of Three Manipuri Dialects
  - Vowel-Based Acoustic and Prosodic Study of Three Manipuri Dialects
  - Vowel-Based Acoustic and Prosodic Study of Three Manipuri Dialects
  - Vowel-Based Acoustic and Prosodic Study of Three Manipuri Dialects
  - Vowel-Based Acoustic and Prosodic Study of Three Manipuri Dialects
  - Vowel-Based Acoustic and Prosodic Study of Three Manipuri Dialects
  - Vowel-Based Acoustic and Prosodic Study of Three Manipuri Dialects
  - Vowel-Based Acoustic and Prosodic Study of Three Manipuri Dialects
  - Vowel-Based Acoustic and Prosodic Study of Three Manipuri Dialects
  - Vowel-Based Acoustic and Prosodic Study of Three Manipuri Dialects
  - An Automatic Speech Transcription System for Manipuri Language - to-text, keyword search, and speaker diarization, integrated into a platform with a user interface for demonstration purposes. |
  - Preliminary Acoustic Analysis of Manipuri Vowels - resourced language |
  - An Experiment on Speech-to-Text Translation Systems for Manipuri to English on Low Resource Setting - to-Text translation systems for Manipuri-English, utilizing a new dataset and benchmark evaluation, comparing pipeline models with ASR and Machine translation against an end-to-end approach, with Gaussian Mixture Model-Hidden Markov Model (GMM-HMM) and Time delay neural network (TDNN) Acoustic models, where the TDNN model outperforms GMM-HMM by 2.53\% WER, albeit with a slight difference of 0.1 BLEU in Speech-to-Text translation evaluation, while both pipeline models surpass the end-to-end approach by 2.6 BLEU score. |
  - Vowel-Based Acoustic and Prosodic Study of Three Manipuri Dialects
  - Verbs in the Early Speeches of Two Manipuri-Speaking Children - speaking children aged 3-5 years, focusing on their emergence and setting the stage for future research, particularly in comparison to Uziel-Karl's (2001) presentation of Hebrew motion verbs. |
  - MECOS: A bilingual Manipuri–English spontaneous code-switching speech corpus for automatic speech recognition - switched speech database for Manipuri–English, comprising 57 hours of annotated spontaneous speech, aiming to construct an automatic speech recognition (ASR) system, with evaluations revealing the superior performance of the pure TDNN model. |
  - Vowel-Based Acoustic and Prosodic Study of Three Manipuri Dialects
  - Vowel-Based Acoustic and Prosodic Study of Three Manipuri Dialects
  - Vowel-Based Acoustic and Prosodic Study of Three Manipuri Dialects
  - Vowel-Based Acoustic and Prosodic Study of Three Manipuri Dialects
  - Vowel-Based Acoustic and Prosodic Study of Three Manipuri Dialects
  - Vowel-Based Acoustic and Prosodic Study of Three Manipuri Dialects
  - Vowel-Based Acoustic and Prosodic Study of Three Manipuri Dialects
  - Vowel-Based Acoustic and Prosodic Study of Three Manipuri Dialects
  - Vowel-Based Acoustic and Prosodic Study of Three Manipuri Dialects
  - Vowel-Based Acoustic and Prosodic Study of Three Manipuri Dialects
  - Vowel-Based Acoustic and Prosodic Study of Three Manipuri Dialects
  - Vowel-Based Acoustic and Prosodic Study of Three Manipuri Dialects
  - Vowel-Based Acoustic and Prosodic Study of Three Manipuri Dialects
  - Vowel-Based Acoustic and Prosodic Study of Three Manipuri Dialects
  - Vowel-Based Acoustic and Prosodic Study of Three Manipuri Dialects
  - Vowel-Based Acoustic and Prosodic Study of Three Manipuri Dialects
  - Vowel-Based Acoustic and Prosodic Study of Three Manipuri Dialects
  - Vowel-Based Acoustic and Prosodic Study of Three Manipuri Dialects
  - Vowel-Based Acoustic and Prosodic Study of Three Manipuri Dialects
  - Vowel-Based Acoustic and Prosodic Study of Three Manipuri Dialects
  - Vowel-Based Acoustic and Prosodic Study of Three Manipuri Dialects
  - Vowel-Based Acoustic and Prosodic Study of Three Manipuri Dialects
  - Vowel-Based Acoustic and Prosodic Study of Three Manipuri Dialects
- Word Sense Disambiguation
  - Identification of Reduplicated Multiword Expressions Using CRF - score values of 92.91\%, 91.90\%, and 92.40\% respectively. |
  - Identification of Reduplicated Multiword Expressions Using CRF - score values of 92.91\%, 91.90\%, and 92.40\% respectively. |
  - Identification of Reduplicated Multiword Expressions Using CRF - score values of 92.91\%, 91.90\%, and 92.40\% respectively. |
  - Identification of Reduplicated Multiword Expressions Using CRF - score values of 92.91\%, 91.90\%, and 92.40\% respectively. |
  - Identification of Reduplicated Multiword Expressions Using CRF - score values of 92.91\%, 91.90\%, and 92.40\% respectively. |
  - Identification of Reduplicated Multiword Expressions Using CRF - score values of 92.91\%, 91.90\%, and 92.40\% respectively. |
  - Identification of Reduplicated Multiword Expressions Using CRF - score values of 92.91\%, 91.90\%, and 92.40\% respectively. |
  - Identification of Reduplicated Multiword Expressions Using CRF - score values of 92.91\%, 91.90\%, and 92.40\% respectively. |
  - Identification of Reduplicated Multiword Expressions Using CRF - score values of 92.91\%, 91.90\%, and 92.40\% respectively. |
  - Identification of Reduplicated Multiword Expressions Using CRF - score values of 92.91\%, 91.90\%, and 92.40\% respectively. |
  - Identification of Reduplicated Multiword Expressions Using CRF - score values of 92.91\%, 91.90\%, and 92.40\% respectively. |
  - Identification of Reduplicated Multiword Expressions Using CRF - score values of 92.91\%, 91.90\%, and 92.40\% respectively. |
  - Identification of Reduplicated Multiword Expressions Using CRF - score values of 92.91\%, 91.90\%, and 92.40\% respectively. |
  - Identification of Reduplicated Multiword Expressions Using CRF - score values of 92.91\%, 91.90\%, and 92.40\% respectively. |
  - Identification of Reduplicated Multiword Expressions Using CRF - score values of 92.91\%, 91.90\%, and 92.40\% respectively. |
  - Identification of Reduplicated Multiword Expressions Using CRF - score values of 92.91\%, 91.90\%, and 92.40\% respectively. |
  - Identification of Reduplicated Multiword Expressions Using CRF - score values of 92.91\%, 91.90\%, and 92.40\% respectively. |
  - Identification of Reduplicated Multiword Expressions Using CRF - score values of 92.91\%, 91.90\%, and 92.40\% respectively. |
  - Identification of Reduplicated Multiword Expressions Using CRF - score values of 92.91\%, 91.90\%, and 92.40\% respectively. |
  - Identification of Reduplicated Multiword Expressions Using CRF - score values of 92.91\%, 91.90\%, and 92.40\% respectively. |
  - Identification of Reduplicated Multiword Expressions Using CRF - score values of 92.91\%, 91.90\%, and 92.40\% respectively. |
  - Identification of Reduplicated Multiword Expressions Using CRF - score values of 92.91\%, 91.90\%, and 92.40\% respectively. |
  - Identification of Reduplicated Multiword Expressions Using CRF - score values of 92.91\%, 91.90\%, and 92.40\% respectively. |
  - Identification of Reduplicated Multiword Expressions Using CRF - score values of 92.91\%, 91.90\%, and 92.40\% respectively. |
  - Identification of Reduplicated Multiword Expressions Using CRF - score values of 92.91\%, 91.90\%, and 92.40\% respectively. |
  - Identification of Reduplicated Multiword Expressions Using CRF - score values of 92.91\%, 91.90\%, and 92.40\% respectively. |
  - Identification of Reduplicated Multiword Expressions Using CRF - score values of 92.91\%, 91.90\%, and 92.40\% respectively. |
  - Identification of Reduplicated Multiword Expressions Using CRF - score values of 92.91\%, 91.90\%, and 92.40\% respectively. |
  - Identification of Reduplicated Multiword Expressions Using CRF - score values of 92.91\%, 91.90\%, and 92.40\% respectively. |
  - Identification of Reduplicated Multiword Expressions Using CRF - score values of 92.91\%, 91.90\%, and 92.40\% respectively. |
  - Identification of Reduplicated Multiword Expressions Using CRF - score values of 92.91\%, 91.90\%, and 92.40\% respectively. |
  - Identification of Reduplicated Multiword Expressions Using CRF - score values of 92.91\%, 91.90\%, and 92.40\% respectively. |
  - Identification of Reduplicated Multiword Expressions Using CRF - score values of 92.91\%, 91.90\%, and 92.40\% respectively. |
  - Identification of Reduplicated Multiword Expressions Using CRF - score values of 92.91\%, 91.90\%, and 92.40\% respectively. |
  - Identification of Reduplicated Multiword Expressions Using CRF - score values of 92.91\%, 91.90\%, and 92.40\% respectively. |
  - Identification of Reduplicated Multiword Expressions Using CRF - score values of 92.91\%, 91.90\%, and 92.40\% respectively. |
  - Identification of Reduplicated Multiword Expressions Using CRF - score values of 92.91\%, 91.90\%, and 92.40\% respectively. |
  - Identification of Reduplicated Multiword Expressions Using CRF - score values of 92.91\%, 91.90\%, and 92.40\% respectively. |
  - Identification of Reduplicated Multiword Expressions Using CRF - score values of 92.91\%, 91.90\%, and 92.40\% respectively. |
  - Identification of Reduplicated Multiword Expressions Using CRF - score values of 92.91\%, 91.90\%, and 92.40\% respectively. |
  - Identification of Reduplicated MWEs in Manipuri: A Rule Based Approach - based model to identify reduplicated Multiword Expressions (MWEs) in Manipuri language texts, achieving an overall average Recall of 94.24\%, Precision of 82.27\%, and F-Score of 87.68\%. |
  - Identification of MWEs Using CRF in Manipuri and Improvement Using Reduplicated MWEs - measure of 72.24\% after accounting for reduplicated MWEs. |
  - Web Based Manipuri Corpus for Multiword NER and Reduplicated MWEs Identification using SVM - based Manipuri corpus, achieving recall, precision, and F-score values of 94.62\%, 93.53\%, and 94.07\% respectively for reduplicated MWE. |
  - Transliteration of CRF Based Multiword Expression (MWE) in Manipuri - measure of 73.74\%, with an accuracy of 90.01\% when comparing the transliterated output with both Meitei Script and Bengali Script Manipuri. |
  - Identification of Reduplicated Multiword Expressions Using CRF - score values of 92.91\%, 91.90\%, and 92.40\% respectively. |
  - Genetic Algorithm (GA) in Feature Selection for CRF Based Manipuri Multiword Expression (MWE) Identification - measure of 73.74\%, demonstrating improvement over CRF-based MWE identification. |
  - Identification of Reduplicated Multiword Expressions Using CRF - score values of 92.91\%, 91.90\%, and 92.40\% respectively. |
  - Identification of Reduplicated Multiword Expressions Using CRF - score values of 92.91\%, 91.90\%, and 92.40\% respectively. |
  - Identification of Reduplicated Multiword Expressions Using CRF - score values of 92.91\%, 91.90\%, and 92.40\% respectively. |
  - Identification of Reduplicated Multiword Expressions Using CRF - score values of 92.91\%, 91.90\%, and 92.40\% respectively. |
  - Identification of Reduplicated Multiword Expressions Using CRF - score values of 92.91\%, 91.90\%, and 92.40\% respectively. |
  - Identification of Reduplicated Multiword Expressions Using CRF - score values of 92.91\%, 91.90\%, and 92.40\% respectively. |
  - Identification of Reduplicated Multiword Expressions Using CRF - score values of 92.91\%, 91.90\%, and 92.40\% respectively. |
  - Identification of Reduplicated Multiword Expressions Using CRF - score values of 92.91\%, 91.90\%, and 92.40\% respectively. |
  - Identification of Reduplicated Multiword Expressions Using CRF - score values of 92.91\%, 91.90\%, and 92.40\% respectively. |
  - Identification of Reduplicated Multiword Expressions Using CRF - score values of 92.91\%, 91.90\%, and 92.40\% respectively. |
  - Identification of Reduplicated Multiword Expressions Using CRF - score values of 92.91\%, 91.90\%, and 92.40\% respectively. |
  - Identification of Reduplicated Multiword Expressions Using CRF - score values of 92.91\%, 91.90\%, and 92.40\% respectively. |
  - Identification of Reduplicated Multiword Expressions Using CRF - score values of 92.91\%, 91.90\%, and 92.40\% respectively. |
  - Identification of Reduplicated Multiword Expressions Using CRF - score values of 92.91\%, 91.90\%, and 92.40\% respectively. |
  - Identification of Reduplicated Multiword Expressions Using CRF - score values of 92.91\%, 91.90\%, and 92.40\% respectively. |
  - Identification of Reduplicated Multiword Expressions Using CRF - score values of 92.91\%, 91.90\%, and 92.40\% respectively. |
  - Identification of Reduplicated Multiword Expressions Using CRF - score values of 92.91\%, 91.90\%, and 92.40\% respectively. |
  - Identification of Reduplicated Multiword Expressions Using CRF - score values of 92.91\%, 91.90\%, and 92.40\% respectively. |
  - Identification of Reduplicated Multiword Expressions Using CRF - score values of 92.91\%, 91.90\%, and 92.40\% respectively. |
  - Identification of Reduplicated Multiword Expressions Using CRF - score values of 92.91\%, 91.90\%, and 92.40\% respectively. |
- Corpus Creation and E-Dictionary
  - Embeddings-Based Parallel Corpus Creation for English-Manipuri - Manipuri automatic sentence aligner based on embeddings to create an English-Manipuri parallel corpus, reducing manual alignment effort by 47.72\% and facilitating neural machine translation in Low-Resource languages.|
  - Manipuri–English comparable corpus for cross-lingual studies - EnCC, a Manipuri–English comparable corpus, created by collating text from Sangai Express and Poknapham news sources, and verified through a semi-automated process, aiming to facilitate cross-lingual studies between Manipuri and English languages.|
  - Embeddings-Based Parallel Corpus Creation for English-Manipuri - Manipuri automatic sentence aligner based on embeddings to create an English-Manipuri parallel corpus, reducing manual alignment effort by 47.72\% and facilitating neural machine translation in Low-Resource languages.|
  - Manipuri–English comparable corpus for cross-lingual studies - EnCC, a Manipuri–English comparable corpus, created by collating text from Sangai Express and Poknapham news sources, and verified through a semi-automated process, aiming to facilitate cross-lingual studies between Manipuri and English languages.|
  - Embeddings-Based Parallel Corpus Creation for English-Manipuri - Manipuri automatic sentence aligner based on embeddings to create an English-Manipuri parallel corpus, reducing manual alignment effort by 47.72\% and facilitating neural machine translation in Low-Resource languages.|
  - Manipuri–English comparable corpus for cross-lingual studies - EnCC, a Manipuri–English comparable corpus, created by collating text from Sangai Express and Poknapham news sources, and verified through a semi-automated process, aiming to facilitate cross-lingual studies between Manipuri and English languages.|
  - Embeddings-Based Parallel Corpus Creation for English-Manipuri - Manipuri automatic sentence aligner based on embeddings to create an English-Manipuri parallel corpus, reducing manual alignment effort by 47.72\% and facilitating neural machine translation in Low-Resource languages.|
  - IndoWordNet
  - Embeddings-Based Parallel Corpus Creation for English-Manipuri - Manipuri automatic sentence aligner based on embeddings to create an English-Manipuri parallel corpus, reducing manual alignment effort by 47.72\% and facilitating neural machine translation in Low-Resource languages.|
  - Manipuri–English comparable corpus for cross-lingual studies - EnCC, a Manipuri–English comparable corpus, created by collating text from Sangai Express and Poknapham news sources, and verified through a semi-automated process, aiming to facilitate cross-lingual studies between Manipuri and English languages.|
  - Embeddings-Based Parallel Corpus Creation for English-Manipuri - Manipuri automatic sentence aligner based on embeddings to create an English-Manipuri parallel corpus, reducing manual alignment effort by 47.72\% and facilitating neural machine translation in Low-Resource languages.|
  - Manipuri–English comparable corpus for cross-lingual studies - EnCC, a Manipuri–English comparable corpus, created by collating text from Sangai Express and Poknapham news sources, and verified through a semi-automated process, aiming to facilitate cross-lingual studies between Manipuri and English languages.|
  - Embeddings-Based Parallel Corpus Creation for English-Manipuri - Manipuri automatic sentence aligner based on embeddings to create an English-Manipuri parallel corpus, reducing manual alignment effort by 47.72\% and facilitating neural machine translation in Low-Resource languages.|
  - Manipuri–English comparable corpus for cross-lingual studies - EnCC, a Manipuri–English comparable corpus, created by collating text from Sangai Express and Poknapham news sources, and verified through a semi-automated process, aiming to facilitate cross-lingual studies between Manipuri and English languages.|
  - Embeddings-Based Parallel Corpus Creation for English-Manipuri - Manipuri automatic sentence aligner based on embeddings to create an English-Manipuri parallel corpus, reducing manual alignment effort by 47.72\% and facilitating neural machine translation in Low-Resource languages.|
  - Manipuri–English comparable corpus for cross-lingual studies - EnCC, a Manipuri–English comparable corpus, created by collating text from Sangai Express and Poknapham news sources, and verified through a semi-automated process, aiming to facilitate cross-lingual studies between Manipuri and English languages.|
  - Embeddings-Based Parallel Corpus Creation for English-Manipuri - Manipuri automatic sentence aligner based on embeddings to create an English-Manipuri parallel corpus, reducing manual alignment effort by 47.72\% and facilitating neural machine translation in Low-Resource languages.|
  - Embeddings-Based Parallel Corpus Creation for English-Manipuri - Manipuri automatic sentence aligner based on embeddings to create an English-Manipuri parallel corpus, reducing manual alignment effort by 47.72\% and facilitating neural machine translation in Low-Resource languages.|
  - Manipuri–English comparable corpus for cross-lingual studies - EnCC, a Manipuri–English comparable corpus, created by collating text from Sangai Express and Poknapham news sources, and verified through a semi-automated process, aiming to facilitate cross-lingual studies between Manipuri and English languages.|
  - Embeddings-Based Parallel Corpus Creation for English-Manipuri - Manipuri automatic sentence aligner based on embeddings to create an English-Manipuri parallel corpus, reducing manual alignment effort by 47.72\% and facilitating neural machine translation in Low-Resource languages.|
  - Manipuri–English comparable corpus for cross-lingual studies - EnCC, a Manipuri–English comparable corpus, created by collating text from Sangai Express and Poknapham news sources, and verified through a semi-automated process, aiming to facilitate cross-lingual studies between Manipuri and English languages.|
  - Embeddings-Based Parallel Corpus Creation for English-Manipuri - Manipuri automatic sentence aligner based on embeddings to create an English-Manipuri parallel corpus, reducing manual alignment effort by 47.72\% and facilitating neural machine translation in Low-Resource languages.|
  - Embeddings-Based Parallel Corpus Creation for English-Manipuri - Manipuri automatic sentence aligner based on embeddings to create an English-Manipuri parallel corpus, reducing manual alignment effort by 47.72\% and facilitating neural machine translation in Low-Resource languages.|
  - Manipuri–English comparable corpus for cross-lingual studies - EnCC, a Manipuri–English comparable corpus, created by collating text from Sangai Express and Poknapham news sources, and verified through a semi-automated process, aiming to facilitate cross-lingual studies between Manipuri and English languages.|
  - Embeddings-Based Parallel Corpus Creation for English-Manipuri - Manipuri automatic sentence aligner based on embeddings to create an English-Manipuri parallel corpus, reducing manual alignment effort by 47.72\% and facilitating neural machine translation in Low-Resource languages.|
  - Manipuri–English comparable corpus for cross-lingual studies - EnCC, a Manipuri–English comparable corpus, created by collating text from Sangai Express and Poknapham news sources, and verified through a semi-automated process, aiming to facilitate cross-lingual studies between Manipuri and English languages.|
  - Embeddings-Based Parallel Corpus Creation for English-Manipuri - Manipuri automatic sentence aligner based on embeddings to create an English-Manipuri parallel corpus, reducing manual alignment effort by 47.72\% and facilitating neural machine translation in Low-Resource languages.|
  - Embeddings-Based Parallel Corpus Creation for English-Manipuri - Manipuri automatic sentence aligner based on embeddings to create an English-Manipuri parallel corpus, reducing manual alignment effort by 47.72\% and facilitating neural machine translation in Low-Resource languages.|
  - Manipuri–English comparable corpus for cross-lingual studies - EnCC, a Manipuri–English comparable corpus, created by collating text from Sangai Express and Poknapham news sources, and verified through a semi-automated process, aiming to facilitate cross-lingual studies between Manipuri and English languages.|
  - Embeddings-Based Parallel Corpus Creation for English-Manipuri - Manipuri automatic sentence aligner based on embeddings to create an English-Manipuri parallel corpus, reducing manual alignment effort by 47.72\% and facilitating neural machine translation in Low-Resource languages.|
  - Embeddings-Based Parallel Corpus Creation for English-Manipuri - Manipuri automatic sentence aligner based on embeddings to create an English-Manipuri parallel corpus, reducing manual alignment effort by 47.72\% and facilitating neural machine translation in Low-Resource languages.|
  - Manipuri–English comparable corpus for cross-lingual studies - EnCC, a Manipuri–English comparable corpus, created by collating text from Sangai Express and Poknapham news sources, and verified through a semi-automated process, aiming to facilitate cross-lingual studies between Manipuri and English languages.|
  - Embeddings-Based Parallel Corpus Creation for English-Manipuri - Manipuri automatic sentence aligner based on embeddings to create an English-Manipuri parallel corpus, reducing manual alignment effort by 47.72\% and facilitating neural machine translation in Low-Resource languages.|
  - Manipuri–English comparable corpus for cross-lingual studies - EnCC, a Manipuri–English comparable corpus, created by collating text from Sangai Express and Poknapham news sources, and verified through a semi-automated process, aiming to facilitate cross-lingual studies between Manipuri and English languages.|
  - Embeddings-Based Parallel Corpus Creation for English-Manipuri - Manipuri automatic sentence aligner based on embeddings to create an English-Manipuri parallel corpus, reducing manual alignment effort by 47.72\% and facilitating neural machine translation in Low-Resource languages.|
  - Manipuri–English comparable corpus for cross-lingual studies - EnCC, a Manipuri–English comparable corpus, created by collating text from Sangai Express and Poknapham news sources, and verified through a semi-automated process, aiming to facilitate cross-lingual studies between Manipuri and English languages.|
  - Embeddings-Based Parallel Corpus Creation for English-Manipuri - Manipuri automatic sentence aligner based on embeddings to create an English-Manipuri parallel corpus, reducing manual alignment effort by 47.72\% and facilitating neural machine translation in Low-Resource languages.|
  - Embeddings-Based Parallel Corpus Creation for English-Manipuri - Manipuri automatic sentence aligner based on embeddings to create an English-Manipuri parallel corpus, reducing manual alignment effort by 47.72\% and facilitating neural machine translation in Low-Resource languages.|
  - Manipuri–English comparable corpus for cross-lingual studies - EnCC, a Manipuri–English comparable corpus, created by collating text from Sangai Express and Poknapham news sources, and verified through a semi-automated process, aiming to facilitate cross-lingual studies between Manipuri and English languages.|
  - Embeddings-Based Parallel Corpus Creation for English-Manipuri - Manipuri automatic sentence aligner based on embeddings to create an English-Manipuri parallel corpus, reducing manual alignment effort by 47.72\% and facilitating neural machine translation in Low-Resource languages.|
  - Embeddings-Based Parallel Corpus Creation for English-Manipuri - Manipuri automatic sentence aligner based on embeddings to create an English-Manipuri parallel corpus, reducing manual alignment effort by 47.72\% and facilitating neural machine translation in Low-Resource languages.|
  - Manipuri–English comparable corpus for cross-lingual studies - EnCC, a Manipuri–English comparable corpus, created by collating text from Sangai Express and Poknapham news sources, and verified through a semi-automated process, aiming to facilitate cross-lingual studies between Manipuri and English languages.|
  - Embeddings-Based Parallel Corpus Creation for English-Manipuri - Manipuri automatic sentence aligner based on embeddings to create an English-Manipuri parallel corpus, reducing manual alignment effort by 47.72\% and facilitating neural machine translation in Low-Resource languages.|
  - Embeddings-Based Parallel Corpus Creation for English-Manipuri - Manipuri automatic sentence aligner based on embeddings to create an English-Manipuri parallel corpus, reducing manual alignment effort by 47.72\% and facilitating neural machine translation in Low-Resource languages.|
  - Manipuri–English comparable corpus for cross-lingual studies - EnCC, a Manipuri–English comparable corpus, created by collating text from Sangai Express and Poknapham news sources, and verified through a semi-automated process, aiming to facilitate cross-lingual studies between Manipuri and English languages.|
  - Manipuri–English comparable corpus for cross-lingual studies - EnCC, a Manipuri–English comparable corpus, created by collating text from Sangai Express and Poknapham news sources, and verified through a semi-automated process, aiming to facilitate cross-lingual studies between Manipuri and English languages.|
  - Embeddings-Based Parallel Corpus Creation for English-Manipuri - Manipuri automatic sentence aligner based on embeddings to create an English-Manipuri parallel corpus, reducing manual alignment effort by 47.72\% and facilitating neural machine translation in Low-Resource languages.|
  - Manipuri–English comparable corpus for cross-lingual studies - EnCC, a Manipuri–English comparable corpus, created by collating text from Sangai Express and Poknapham news sources, and verified through a semi-automated process, aiming to facilitate cross-lingual studies between Manipuri and English languages.|
  - Embeddings-Based Parallel Corpus Creation for English-Manipuri - Manipuri automatic sentence aligner based on embeddings to create an English-Manipuri parallel corpus, reducing manual alignment effort by 47.72\% and facilitating neural machine translation in Low-Resource languages.|
  - Embeddings-Based Parallel Corpus Creation for English-Manipuri - Manipuri automatic sentence aligner based on embeddings to create an English-Manipuri parallel corpus, reducing manual alignment effort by 47.72\% and facilitating neural machine translation in Low-Resource languages.|
  - Manipuri–English comparable corpus for cross-lingual studies - EnCC, a Manipuri–English comparable corpus, created by collating text from Sangai Express and Poknapham news sources, and verified through a semi-automated process, aiming to facilitate cross-lingual studies between Manipuri and English languages.|
  - Embeddings-Based Parallel Corpus Creation for English-Manipuri - Manipuri automatic sentence aligner based on embeddings to create an English-Manipuri parallel corpus, reducing manual alignment effort by 47.72\% and facilitating neural machine translation in Low-Resource languages.|
  - Manipuri–English comparable corpus for cross-lingual studies - EnCC, a Manipuri–English comparable corpus, created by collating text from Sangai Express and Poknapham news sources, and verified through a semi-automated process, aiming to facilitate cross-lingual studies between Manipuri and English languages.|
  - Embeddings-Based Parallel Corpus Creation for English-Manipuri - Manipuri automatic sentence aligner based on embeddings to create an English-Manipuri parallel corpus, reducing manual alignment effort by 47.72\% and facilitating neural machine translation in Low-Resource languages.|
  - Manipuri–English comparable corpus for cross-lingual studies - EnCC, a Manipuri–English comparable corpus, created by collating text from Sangai Express and Poknapham news sources, and verified through a semi-automated process, aiming to facilitate cross-lingual studies between Manipuri and English languages.|
  - Embeddings-Based Parallel Corpus Creation for English-Manipuri - Manipuri automatic sentence aligner based on embeddings to create an English-Manipuri parallel corpus, reducing manual alignment effort by 47.72\% and facilitating neural machine translation in Low-Resource languages.|
  - Embeddings-Based Parallel Corpus Creation for English-Manipuri - Manipuri automatic sentence aligner based on embeddings to create an English-Manipuri parallel corpus, reducing manual alignment effort by 47.72\% and facilitating neural machine translation in Low-Resource languages.|
  - Embeddings-Based Parallel Corpus Creation for English-Manipuri - Manipuri automatic sentence aligner based on embeddings to create an English-Manipuri parallel corpus, reducing manual alignment effort by 47.72\% and facilitating neural machine translation in Low-Resource languages.|
  - Manipuri–English comparable corpus for cross-lingual studies - EnCC, a Manipuri–English comparable corpus, created by collating text from Sangai Express and Poknapham news sources, and verified through a semi-automated process, aiming to facilitate cross-lingual studies between Manipuri and English languages.|
  - Embeddings-Based Parallel Corpus Creation for English-Manipuri - Manipuri automatic sentence aligner based on embeddings to create an English-Manipuri parallel corpus, reducing manual alignment effort by 47.72\% and facilitating neural machine translation in Low-Resource languages.|
  - Embeddings-Based Parallel Corpus Creation for English-Manipuri - Manipuri automatic sentence aligner based on embeddings to create an English-Manipuri parallel corpus, reducing manual alignment effort by 47.72\% and facilitating neural machine translation in Low-Resource languages.|
  - Embeddings-Based Parallel Corpus Creation for English-Manipuri - Manipuri automatic sentence aligner based on embeddings to create an English-Manipuri parallel corpus, reducing manual alignment effort by 47.72\% and facilitating neural machine translation in Low-Resource languages.|
  - Embeddings-Based Parallel Corpus Creation for English-Manipuri - Manipuri automatic sentence aligner based on embeddings to create an English-Manipuri parallel corpus, reducing manual alignment effort by 47.72\% and facilitating neural machine translation in Low-Resource languages.|
  - Manipuri–English comparable corpus for cross-lingual studies - EnCC, a Manipuri–English comparable corpus, created by collating text from Sangai Express and Poknapham news sources, and verified through a semi-automated process, aiming to facilitate cross-lingual studies between Manipuri and English languages.|
  - Embeddings-Based Parallel Corpus Creation for English-Manipuri - Manipuri automatic sentence aligner based on embeddings to create an English-Manipuri parallel corpus, reducing manual alignment effort by 47.72\% and facilitating neural machine translation in Low-Resource languages.|
  - Embeddings-Based Parallel Corpus Creation for English-Manipuri - Manipuri automatic sentence aligner based on embeddings to create an English-Manipuri parallel corpus, reducing manual alignment effort by 47.72\% and facilitating neural machine translation in Low-Resource languages.|
  - Semi–Automatic Parallel Corpora Extraction from Comparable News Corpora - collected news corpora, leveraging morphological information to improve alignment quality, thus demonstrating effectiveness for resource-constrained, agglutinative, and inflective Indian languages.|
  - Building Parallel Corpora for SMT System: A Case Study of English-Manipuri - based comparable news corpora to improve translation quality in Statistical Machine Translation (SMT) systems for resource-constrained language pairs.|
  - Embeddings-Based Parallel Corpus Creation for English-Manipuri - Manipuri automatic sentence aligner based on embeddings to create an English-Manipuri parallel corpus, reducing manual alignment effort by 47.72\% and facilitating neural machine translation in Low-Resource languages.|
  - EM Corpus: a comparable corpus for a less-resourced language pair Manipuri-English - level comparable text corpus for the Manipuri-English language pair, consisting of 1.88 million Manipuri sentences, 1.45 million English sentences, and 124,975 Manipuri-English sentence pairs crawled from 'The Sangai Express' website, aimed at supporting MT/NLP tasks for low-resourced languages. |
  - Manipuri–English comparable corpus for cross-lingual studies - EnCC, a Manipuri–English comparable corpus, created by collating text from Sangai Express and Poknapham news sources, and verified through a semi-automated process, aiming to facilitate cross-lingual studies between Manipuri and English languages.|
  - Building Manipuri-English Machine Readable Dictionary by Implementing Ontology - English machine-readable dictionary using ontology, aiming to provide an effective combination of traditional bilingual lexicographic information and conceptual knowledge essential for Natural Language Processing applications.|
  - An Analysis towards the Development of Electronic Bilingual Dictionary(Manipuri-English)-A Report - Manipuri bilingual lexicographic information and conceptual knowledge essential for Natural Language Processing applications. |
  - Word Search in a WWW Manipuri-English Electronic Dictionary - English bilingual dictionary, emphasizing its word search functionality categorized into simple word search, wild card search, and search by lexical item, thereby contributing to language learning and natural language processing. |
  - DEVELOPMENT OF ENGLISH TO MANIPURI ELECTRONIC DICTIONARY: A database approach
  - Embeddings-Based Parallel Corpus Creation for English-Manipuri - Manipuri automatic sentence aligner based on embeddings to create an English-Manipuri parallel corpus, reducing manual alignment effort by 47.72\% and facilitating neural machine translation in Low-Resource languages.|
  - Embeddings-Based Parallel Corpus Creation for English-Manipuri - Manipuri automatic sentence aligner based on embeddings to create an English-Manipuri parallel corpus, reducing manual alignment effort by 47.72\% and facilitating neural machine translation in Low-Resource languages.|
  - Embeddings-Based Parallel Corpus Creation for English-Manipuri - Manipuri automatic sentence aligner based on embeddings to create an English-Manipuri parallel corpus, reducing manual alignment effort by 47.72\% and facilitating neural machine translation in Low-Resource languages.|
  - Manipuri–English comparable corpus for cross-lingual studies - EnCC, a Manipuri–English comparable corpus, created by collating text from Sangai Express and Poknapham news sources, and verified through a semi-automated process, aiming to facilitate cross-lingual studies between Manipuri and English languages.|
  - Embeddings-Based Parallel Corpus Creation for English-Manipuri - Manipuri automatic sentence aligner based on embeddings to create an English-Manipuri parallel corpus, reducing manual alignment effort by 47.72\% and facilitating neural machine translation in Low-Resource languages.|
  - Embeddings-Based Parallel Corpus Creation for English-Manipuri - Manipuri automatic sentence aligner based on embeddings to create an English-Manipuri parallel corpus, reducing manual alignment effort by 47.72\% and facilitating neural machine translation in Low-Resource languages.|
  - Manipuri–English comparable corpus for cross-lingual studies - EnCC, a Manipuri–English comparable corpus, created by collating text from Sangai Express and Poknapham news sources, and verified through a semi-automated process, aiming to facilitate cross-lingual studies between Manipuri and English languages.|
  - Manipuri–English comparable corpus for cross-lingual studies - EnCC, a Manipuri–English comparable corpus, created by collating text from Sangai Express and Poknapham news sources, and verified through a semi-automated process, aiming to facilitate cross-lingual studies between Manipuri and English languages.|
  - Embeddings-Based Parallel Corpus Creation for English-Manipuri - Manipuri automatic sentence aligner based on embeddings to create an English-Manipuri parallel corpus, reducing manual alignment effort by 47.72\% and facilitating neural machine translation in Low-Resource languages.|
  - Embeddings-Based Parallel Corpus Creation for English-Manipuri - Manipuri automatic sentence aligner based on embeddings to create an English-Manipuri parallel corpus, reducing manual alignment effort by 47.72\% and facilitating neural machine translation in Low-Resource languages.|
  - Manipuri–English comparable corpus for cross-lingual studies - EnCC, a Manipuri–English comparable corpus, created by collating text from Sangai Express and Poknapham news sources, and verified through a semi-automated process, aiming to facilitate cross-lingual studies between Manipuri and English languages.|
  - Embeddings-Based Parallel Corpus Creation for English-Manipuri - Manipuri automatic sentence aligner based on embeddings to create an English-Manipuri parallel corpus, reducing manual alignment effort by 47.72\% and facilitating neural machine translation in Low-Resource languages.|
  - Manipuri–English comparable corpus for cross-lingual studies - EnCC, a Manipuri–English comparable corpus, created by collating text from Sangai Express and Poknapham news sources, and verified through a semi-automated process, aiming to facilitate cross-lingual studies between Manipuri and English languages.|
  - Embeddings-Based Parallel Corpus Creation for English-Manipuri - Manipuri automatic sentence aligner based on embeddings to create an English-Manipuri parallel corpus, reducing manual alignment effort by 47.72\% and facilitating neural machine translation in Low-Resource languages.|
  - Embeddings-Based Parallel Corpus Creation for English-Manipuri - Manipuri automatic sentence aligner based on embeddings to create an English-Manipuri parallel corpus, reducing manual alignment effort by 47.72\% and facilitating neural machine translation in Low-Resource languages.|
  - Manipuri–English comparable corpus for cross-lingual studies - EnCC, a Manipuri–English comparable corpus, created by collating text from Sangai Express and Poknapham news sources, and verified through a semi-automated process, aiming to facilitate cross-lingual studies between Manipuri and English languages.|
  - Embeddings-Based Parallel Corpus Creation for English-Manipuri - Manipuri automatic sentence aligner based on embeddings to create an English-Manipuri parallel corpus, reducing manual alignment effort by 47.72\% and facilitating neural machine translation in Low-Resource languages.|
  - Manipuri–English comparable corpus for cross-lingual studies - EnCC, a Manipuri–English comparable corpus, created by collating text from Sangai Express and Poknapham news sources, and verified through a semi-automated process, aiming to facilitate cross-lingual studies between Manipuri and English languages.|
  - Embeddings-Based Parallel Corpus Creation for English-Manipuri - Manipuri automatic sentence aligner based on embeddings to create an English-Manipuri parallel corpus, reducing manual alignment effort by 47.72\% and facilitating neural machine translation in Low-Resource languages.|
  - Manipuri–English comparable corpus for cross-lingual studies - EnCC, a Manipuri–English comparable corpus, created by collating text from Sangai Express and Poknapham news sources, and verified through a semi-automated process, aiming to facilitate cross-lingual studies between Manipuri and English languages.|
  - Manipuri–English comparable corpus for cross-lingual studies - EnCC, a Manipuri–English comparable corpus, created by collating text from Sangai Express and Poknapham news sources, and verified through a semi-automated process, aiming to facilitate cross-lingual studies between Manipuri and English languages.|
  - Manipuri–English comparable corpus for cross-lingual studies - EnCC, a Manipuri–English comparable corpus, created by collating text from Sangai Express and Poknapham news sources, and verified through a semi-automated process, aiming to facilitate cross-lingual studies between Manipuri and English languages.|
  - Embeddings-Based Parallel Corpus Creation for English-Manipuri - Manipuri automatic sentence aligner based on embeddings to create an English-Manipuri parallel corpus, reducing manual alignment effort by 47.72\% and facilitating neural machine translation in Low-Resource languages.|
  - Semi–Automatic Parallel Corpora Extraction from Comparable News Corpora - collected news corpora, leveraging morphological information to improve alignment quality, thus demonstrating effectiveness for resource-constrained, agglutinative, and inflective Indian languages.|
  - Embeddings-Based Parallel Corpus Creation for English-Manipuri - Manipuri automatic sentence aligner based on embeddings to create an English-Manipuri parallel corpus, reducing manual alignment effort by 47.72\% and facilitating neural machine translation in Low-Resource languages.|
  - Manipuri–English comparable corpus for cross-lingual studies - EnCC, a Manipuri–English comparable corpus, created by collating text from Sangai Express and Poknapham news sources, and verified through a semi-automated process, aiming to facilitate cross-lingual studies between Manipuri and English languages.|
  - Embeddings-Based Parallel Corpus Creation for English-Manipuri - Manipuri automatic sentence aligner based on embeddings to create an English-Manipuri parallel corpus, reducing manual alignment effort by 47.72\% and facilitating neural machine translation in Low-Resource languages.|
  - Manipuri–English comparable corpus for cross-lingual studies - EnCC, a Manipuri–English comparable corpus, created by collating text from Sangai Express and Poknapham news sources, and verified through a semi-automated process, aiming to facilitate cross-lingual studies between Manipuri and English languages.|
  - Embeddings-Based Parallel Corpus Creation for English-Manipuri - Manipuri automatic sentence aligner based on embeddings to create an English-Manipuri parallel corpus, reducing manual alignment effort by 47.72\% and facilitating neural machine translation in Low-Resource languages.|
  - Manipuri–English comparable corpus for cross-lingual studies - EnCC, a Manipuri–English comparable corpus, created by collating text from Sangai Express and Poknapham news sources, and verified through a semi-automated process, aiming to facilitate cross-lingual studies between Manipuri and English languages.|
  - Embeddings-Based Parallel Corpus Creation for English-Manipuri - Manipuri automatic sentence aligner based on embeddings to create an English-Manipuri parallel corpus, reducing manual alignment effort by 47.72\% and facilitating neural machine translation in Low-Resource languages.|
  - Embeddings-Based Parallel Corpus Creation for English-Manipuri - Manipuri automatic sentence aligner based on embeddings to create an English-Manipuri parallel corpus, reducing manual alignment effort by 47.72\% and facilitating neural machine translation in Low-Resource languages.|
  - Manipuri–English comparable corpus for cross-lingual studies - EnCC, a Manipuri–English comparable corpus, created by collating text from Sangai Express and Poknapham news sources, and verified through a semi-automated process, aiming to facilitate cross-lingual studies between Manipuri and English languages.|
  - Embeddings-Based Parallel Corpus Creation for English-Manipuri - Manipuri automatic sentence aligner based on embeddings to create an English-Manipuri parallel corpus, reducing manual alignment effort by 47.72\% and facilitating neural machine translation in Low-Resource languages.|
  - Manipuri–English comparable corpus for cross-lingual studies - EnCC, a Manipuri–English comparable corpus, created by collating text from Sangai Express and Poknapham news sources, and verified through a semi-automated process, aiming to facilitate cross-lingual studies between Manipuri and English languages.|
  - Embeddings-Based Parallel Corpus Creation for English-Manipuri - Manipuri automatic sentence aligner based on embeddings to create an English-Manipuri parallel corpus, reducing manual alignment effort by 47.72\% and facilitating neural machine translation in Low-Resource languages.|
  - Manipuri–English comparable corpus for cross-lingual studies - EnCC, a Manipuri–English comparable corpus, created by collating text from Sangai Express and Poknapham news sources, and verified through a semi-automated process, aiming to facilitate cross-lingual studies between Manipuri and English languages.|
- Parsing
  - Problems and Issues in Parsing Manipuri Text - resource languages like Manipuri. |
  - A Grammar-Driven Approach for Parsing Manipuri Language - free grammar (CFG) and Earley’s parsing algorithm for parsing Manipuri language, achieving a Recall of 81.71\%, Precision of 72.38\%, and F-measure of 76.76\%. |
  - Problems and Issues in Parsing Manipuri Text - resource languages like Manipuri. |
  - A Grammar-Driven Approach for Parsing Manipuri Language - free grammar (CFG) and Earley’s parsing algorithm for parsing Manipuri language, achieving a Recall of 81.71\%, Precision of 72.38\%, and F-measure of 76.76\%. |
  - Problems and Issues in Parsing Manipuri Text - resource languages like Manipuri. |
  - A Grammar-Driven Approach for Parsing Manipuri Language - free grammar (CFG) and Earley’s parsing algorithm for parsing Manipuri language, achieving a Recall of 81.71\%, Precision of 72.38\%, and F-measure of 76.76\%. |
  - Problems and Issues in Parsing Manipuri Text - resource languages like Manipuri. |
  - A Grammar-Driven Approach for Parsing Manipuri Language - free grammar (CFG) and Earley’s parsing algorithm for parsing Manipuri language, achieving a Recall of 81.71\%, Precision of 72.38\%, and F-measure of 76.76\%. |
  - A Grammar-Driven Approach for Parsing Manipuri Language - free grammar (CFG) and Earley’s parsing algorithm for parsing Manipuri language, achieving a Recall of 81.71\%, Precision of 72.38\%, and F-measure of 76.76\%. |
  - Problems and Issues in Parsing Manipuri Text - resource languages like Manipuri. |
  - Problems and Issues in Parsing Manipuri Text - resource languages like Manipuri. |
  - A Grammar-Driven Approach for Parsing Manipuri Language - free grammar (CFG) and Earley’s parsing algorithm for parsing Manipuri language, achieving a Recall of 81.71\%, Precision of 72.38\%, and F-measure of 76.76\%. |
  - A Grammar-Driven Approach for Parsing Manipuri Language - free grammar (CFG) and Earley’s parsing algorithm for parsing Manipuri language, achieving a Recall of 81.71\%, Precision of 72.38\%, and F-measure of 76.76\%. |
  - Problems and Issues in Parsing Manipuri Text - resource languages like Manipuri. |
  - A Context-Free Grammar for Parsing Manipuri Language - free grammar (CFG) approach for parsing Manipuri sentences, achieving a recognition rate of 83.20\% with an Earley’s parser. |
  - Problems and Issues in Parsing Manipuri Text - resource languages like Manipuri. |
  - A Grammar-Driven Approach for Parsing Manipuri Language - free grammar (CFG) and Earley’s parsing algorithm for parsing Manipuri language, achieving a Recall of 81.71\%, Precision of 72.38\%, and F-measure of 76.76\%. |
  - Problems and Issues in Parsing Manipuri Text - resource languages like Manipuri. |
  - A Grammar-Driven Approach for Parsing Manipuri Language - free grammar (CFG) and Earley’s parsing algorithm for parsing Manipuri language, achieving a Recall of 81.71\%, Precision of 72.38\%, and F-measure of 76.76\%. |
  - Problems and Issues in Parsing Manipuri Text - resource languages like Manipuri. |
  - A Grammar-Driven Approach for Parsing Manipuri Language - free grammar (CFG) and Earley’s parsing algorithm for parsing Manipuri language, achieving a Recall of 81.71\%, Precision of 72.38\%, and F-measure of 76.76\%. |
  - Problems and Issues in Parsing Manipuri Text - resource languages like Manipuri. |
  - A Grammar-Driven Approach for Parsing Manipuri Language - free grammar (CFG) and Earley’s parsing algorithm for parsing Manipuri language, achieving a Recall of 81.71\%, Precision of 72.38\%, and F-measure of 76.76\%. |
  - Problems and Issues in Parsing Manipuri Text - resource languages like Manipuri. |
  - A Grammar-Driven Approach for Parsing Manipuri Language - free grammar (CFG) and Earley’s parsing algorithm for parsing Manipuri language, achieving a Recall of 81.71\%, Precision of 72.38\%, and F-measure of 76.76\%. |
  - Problems and Issues in Parsing Manipuri Text - resource languages like Manipuri. |
  - A Grammar-Driven Approach for Parsing Manipuri Language - free grammar (CFG) and Earley’s parsing algorithm for parsing Manipuri language, achieving a Recall of 81.71\%, Precision of 72.38\%, and F-measure of 76.76\%. |
  - Problems and Issues in Parsing Manipuri Text - resource languages like Manipuri. |
  - A Grammar-Driven Approach for Parsing Manipuri Language - free grammar (CFG) and Earley’s parsing algorithm for parsing Manipuri language, achieving a Recall of 81.71\%, Precision of 72.38\%, and F-measure of 76.76\%. |
  - Problems and Issues in Parsing Manipuri Text - resource languages like Manipuri. |
  - A Grammar-Driven Approach for Parsing Manipuri Language - free grammar (CFG) and Earley’s parsing algorithm for parsing Manipuri language, achieving a Recall of 81.71\%, Precision of 72.38\%, and F-measure of 76.76\%. |
  - Problems and Issues in Parsing Manipuri Text - resource languages like Manipuri. |
  - A Grammar-Driven Approach for Parsing Manipuri Language - free grammar (CFG) and Earley’s parsing algorithm for parsing Manipuri language, achieving a Recall of 81.71\%, Precision of 72.38\%, and F-measure of 76.76\%. |
  - Problems and Issues in Parsing Manipuri Text - resource languages like Manipuri. |
  - A Grammar-Driven Approach for Parsing Manipuri Language - free grammar (CFG) and Earley’s parsing algorithm for parsing Manipuri language, achieving a Recall of 81.71\%, Precision of 72.38\%, and F-measure of 76.76\%. |
  - Problems and Issues in Parsing Manipuri Text - resource languages like Manipuri. |
  - A Grammar-Driven Approach for Parsing Manipuri Language - free grammar (CFG) and Earley’s parsing algorithm for parsing Manipuri language, achieving a Recall of 81.71\%, Precision of 72.38\%, and F-measure of 76.76\%. |
  - Problems and Issues in Parsing Manipuri Text - resource languages like Manipuri. |
  - A Grammar-Driven Approach for Parsing Manipuri Language - free grammar (CFG) and Earley’s parsing algorithm for parsing Manipuri language, achieving a Recall of 81.71\%, Precision of 72.38\%, and F-measure of 76.76\%. |
  - Problems and Issues in Parsing Manipuri Text - resource languages like Manipuri. |
  - A Grammar-Driven Approach for Parsing Manipuri Language - free grammar (CFG) and Earley’s parsing algorithm for parsing Manipuri language, achieving a Recall of 81.71\%, Precision of 72.38\%, and F-measure of 76.76\%. |
  - Problems and Issues in Parsing Manipuri Text - resource languages like Manipuri. |
  - A Grammar-Driven Approach for Parsing Manipuri Language - free grammar (CFG) and Earley’s parsing algorithm for parsing Manipuri language, achieving a Recall of 81.71\%, Precision of 72.38\%, and F-measure of 76.76\%. |
  - Problems and Issues in Parsing Manipuri Text - resource languages like Manipuri. |
  - A Grammar-Driven Approach for Parsing Manipuri Language - free grammar (CFG) and Earley’s parsing algorithm for parsing Manipuri language, achieving a Recall of 81.71\%, Precision of 72.38\%, and F-measure of 76.76\%. |
  - Problems and Issues in Parsing Manipuri Text - resource languages like Manipuri. |
  - A Grammar-Driven Approach for Parsing Manipuri Language - free grammar (CFG) and Earley’s parsing algorithm for parsing Manipuri language, achieving a Recall of 81.71\%, Precision of 72.38\%, and F-measure of 76.76\%. |
  - Problems and Issues in Parsing Manipuri Text - resource languages like Manipuri. |
  - A Grammar-Driven Approach for Parsing Manipuri Language - free grammar (CFG) and Earley’s parsing algorithm for parsing Manipuri language, achieving a Recall of 81.71\%, Precision of 72.38\%, and F-measure of 76.76\%. |
  - Problems and Issues in Parsing Manipuri Text - resource languages like Manipuri. |
  - A Grammar-Driven Approach for Parsing Manipuri Language - free grammar (CFG) and Earley’s parsing algorithm for parsing Manipuri language, achieving a Recall of 81.71\%, Precision of 72.38\%, and F-measure of 76.76\%. |
  - A Grammar-Driven Approach for Parsing Manipuri Language - free grammar (CFG) and Earley’s parsing algorithm for parsing Manipuri language, achieving a Recall of 81.71\%, Precision of 72.38\%, and F-measure of 76.76\%. |
  - Problems and Issues in Parsing Manipuri Text - resource languages like Manipuri. |
  - Problems and Issues in Parsing Manipuri Text - resource languages like Manipuri. |
  - A Grammar-Driven Approach for Parsing Manipuri Language - free grammar (CFG) and Earley’s parsing algorithm for parsing Manipuri language, achieving a Recall of 81.71\%, Precision of 72.38\%, and F-measure of 76.76\%. |
  - Problems and Issues in Parsing Manipuri Text - resource languages like Manipuri. |
  - A Grammar-Driven Approach for Parsing Manipuri Language - free grammar (CFG) and Earley’s parsing algorithm for parsing Manipuri language, achieving a Recall of 81.71\%, Precision of 72.38\%, and F-measure of 76.76\%. |
  - A Grammar-Driven Approach for Parsing Manipuri Language - free grammar (CFG) and Earley’s parsing algorithm for parsing Manipuri language, achieving a Recall of 81.71\%, Precision of 72.38\%, and F-measure of 76.76\%. |
  - Problems and Issues in Parsing Manipuri Text - resource languages like Manipuri. |
  - Problems and Issues in Parsing Manipuri Text - resource languages like Manipuri. |
  - A Grammar-Driven Approach for Parsing Manipuri Language - free grammar (CFG) and Earley’s parsing algorithm for parsing Manipuri language, achieving a Recall of 81.71\%, Precision of 72.38\%, and F-measure of 76.76\%. |
  - Problems and Issues in Parsing Manipuri Text - resource languages like Manipuri. |
  - A Grammar-Driven Approach for Parsing Manipuri Language - free grammar (CFG) and Earley’s parsing algorithm for parsing Manipuri language, achieving a Recall of 81.71\%, Precision of 72.38\%, and F-measure of 76.76\%. |
  - Problems and Issues in Parsing Manipuri Text - resource languages like Manipuri. |
  - A Grammar-Driven Approach for Parsing Manipuri Language - free grammar (CFG) and Earley’s parsing algorithm for parsing Manipuri language, achieving a Recall of 81.71\%, Precision of 72.38\%, and F-measure of 76.76\%. |
  - Problems and Issues in Parsing Manipuri Text - resource languages like Manipuri. |
  - A Grammar-Driven Approach for Parsing Manipuri Language - free grammar (CFG) and Earley’s parsing algorithm for parsing Manipuri language, achieving a Recall of 81.71\%, Precision of 72.38\%, and F-measure of 76.76\%. |
  - Problems and Issues in Parsing Manipuri Text - resource languages like Manipuri. |
  - A Grammar-Driven Approach for Parsing Manipuri Language - free grammar (CFG) and Earley’s parsing algorithm for parsing Manipuri language, achieving a Recall of 81.71\%, Precision of 72.38\%, and F-measure of 76.76\%. |
  - Problems and Issues in Parsing Manipuri Text - resource languages like Manipuri. |
  - A Grammar-Driven Approach for Parsing Manipuri Language - free grammar (CFG) and Earley’s parsing algorithm for parsing Manipuri language, achieving a Recall of 81.71\%, Precision of 72.38\%, and F-measure of 76.76\%. |
  - Problems and Issues in Parsing Manipuri Text - resource languages like Manipuri. |
  - A Grammar-Driven Approach for Parsing Manipuri Language - free grammar (CFG) and Earley’s parsing algorithm for parsing Manipuri language, achieving a Recall of 81.71\%, Precision of 72.38\%, and F-measure of 76.76\%. |
  - Problems and Issues in Parsing Manipuri Text - resource languages like Manipuri. |
  - A Grammar-Driven Approach for Parsing Manipuri Language - free grammar (CFG) and Earley’s parsing algorithm for parsing Manipuri language, achieving a Recall of 81.71\%, Precision of 72.38\%, and F-measure of 76.76\%. |
  - Problems and Issues in Parsing Manipuri Text - resource languages like Manipuri. |
  - A Grammar-Driven Approach for Parsing Manipuri Language - free grammar (CFG) and Earley’s parsing algorithm for parsing Manipuri language, achieving a Recall of 81.71\%, Precision of 72.38\%, and F-measure of 76.76\%. |
  - Problems and Issues in Parsing Manipuri Text - resource languages like Manipuri. |
  - A Grammar-Driven Approach for Parsing Manipuri Language - free grammar (CFG) and Earley’s parsing algorithm for parsing Manipuri language, achieving a Recall of 81.71\%, Precision of 72.38\%, and F-measure of 76.76\%. |
  - Problems and Issues in Parsing Manipuri Text - resource languages like Manipuri. |
  - A Grammar-Driven Approach for Parsing Manipuri Language - free grammar (CFG) and Earley’s parsing algorithm for parsing Manipuri language, achieving a Recall of 81.71\%, Precision of 72.38\%, and F-measure of 76.76\%. |
  - Problems and Issues in Parsing Manipuri Text - resource languages like Manipuri. |
  - A Grammar-Driven Approach for Parsing Manipuri Language - free grammar (CFG) and Earley’s parsing algorithm for parsing Manipuri language, achieving a Recall of 81.71\%, Precision of 72.38\%, and F-measure of 76.76\%. |
  - A Grammar-Driven Approach for Parsing Manipuri Language - free grammar (CFG) and Earley’s parsing algorithm for parsing Manipuri language, achieving a Recall of 81.71\%, Precision of 72.38\%, and F-measure of 76.76\%. |
  - Problems and Issues in Parsing Manipuri Text - resource languages like Manipuri. |
  - Problems and Issues in Parsing Manipuri Text - resource languages like Manipuri. |
  - A Grammar-Driven Approach for Parsing Manipuri Language - free grammar (CFG) and Earley’s parsing algorithm for parsing Manipuri language, achieving a Recall of 81.71\%, Precision of 72.38\%, and F-measure of 76.76\%. |
  - Problems and Issues in Parsing Manipuri Text - resource languages like Manipuri. |
  - A Grammar-Driven Approach for Parsing Manipuri Language - free grammar (CFG) and Earley’s parsing algorithm for parsing Manipuri language, achieving a Recall of 81.71\%, Precision of 72.38\%, and F-measure of 76.76\%. |
  - Problems and Issues in Parsing Manipuri Text - resource languages like Manipuri. |
  - A Grammar-Driven Approach for Parsing Manipuri Language - free grammar (CFG) and Earley’s parsing algorithm for parsing Manipuri language, achieving a Recall of 81.71\%, Precision of 72.38\%, and F-measure of 76.76\%. |
  - Problems and Issues in Parsing Manipuri Text - resource languages like Manipuri. |
  - A Grammar-Driven Approach for Parsing Manipuri Language - free grammar (CFG) and Earley’s parsing algorithm for parsing Manipuri language, achieving a Recall of 81.71\%, Precision of 72.38\%, and F-measure of 76.76\%. |
  - Problems and Issues in Parsing Manipuri Text - resource languages like Manipuri. |
  - A Grammar-Driven Approach for Parsing Manipuri Language - free grammar (CFG) and Earley’s parsing algorithm for parsing Manipuri language, achieving a Recall of 81.71\%, Precision of 72.38\%, and F-measure of 76.76\%. |
  - Problems and Issues in Parsing Manipuri Text - resource languages like Manipuri. |
  - A Grammar-Driven Approach for Parsing Manipuri Language - free grammar (CFG) and Earley’s parsing algorithm for parsing Manipuri language, achieving a Recall of 81.71\%, Precision of 72.38\%, and F-measure of 76.76\%. |
  - Problems and Issues in Parsing Manipuri Text - resource languages like Manipuri. |
  - A Grammar-Driven Approach for Parsing Manipuri Language - free grammar (CFG) and Earley’s parsing algorithm for parsing Manipuri language, achieving a Recall of 81.71\%, Precision of 72.38\%, and F-measure of 76.76\%. |
  - Problems and Issues in Parsing Manipuri Text - resource languages like Manipuri. |
  - A Grammar-Driven Approach for Parsing Manipuri Language - free grammar (CFG) and Earley’s parsing algorithm for parsing Manipuri language, achieving a Recall of 81.71\%, Precision of 72.38\%, and F-measure of 76.76\%. |
  - A Grammar-Driven Approach for Parsing Manipuri Language - free grammar (CFG) and Earley’s parsing algorithm for parsing Manipuri language, achieving a Recall of 81.71\%, Precision of 72.38\%, and F-measure of 76.76\%. |
  - Problems and Issues in Parsing Manipuri Text - resource languages like Manipuri. |
  - Problems and Issues in Parsing Manipuri Text - resource languages like Manipuri. |
  - A Grammar-Driven Approach for Parsing Manipuri Language - free grammar (CFG) and Earley’s parsing algorithm for parsing Manipuri language, achieving a Recall of 81.71\%, Precision of 72.38\%, and F-measure of 76.76\%. |
  - Problems and Issues in Parsing Manipuri Text - resource languages like Manipuri. |
  - A Grammar-Driven Approach for Parsing Manipuri Language - free grammar (CFG) and Earley’s parsing algorithm for parsing Manipuri language, achieving a Recall of 81.71\%, Precision of 72.38\%, and F-measure of 76.76\%. |
  - Problems and Issues in Parsing Manipuri Text - resource languages like Manipuri. |
  - A Grammar-Driven Approach for Parsing Manipuri Language - free grammar (CFG) and Earley’s parsing algorithm for parsing Manipuri language, achieving a Recall of 81.71\%, Precision of 72.38\%, and F-measure of 76.76\%. |
  - Problems and Issues in Parsing Manipuri Text - resource languages like Manipuri. |
  - A Grammar-Driven Approach for Parsing Manipuri Language - free grammar (CFG) and Earley’s parsing algorithm for parsing Manipuri language, achieving a Recall of 81.71\%, Precision of 72.38\%, and F-measure of 76.76\%. |
  - Problems and Issues in Parsing Manipuri Text - resource languages like Manipuri. |
  - A Grammar-Driven Approach for Parsing Manipuri Language - free grammar (CFG) and Earley’s parsing algorithm for parsing Manipuri language, achieving a Recall of 81.71\%, Precision of 72.38\%, and F-measure of 76.76\%. |
  - Problems and Issues in Parsing Manipuri Text - resource languages like Manipuri. |
  - A Grammar-Driven Approach for Parsing Manipuri Language - free grammar (CFG) and Earley’s parsing algorithm for parsing Manipuri language, achieving a Recall of 81.71\%, Precision of 72.38\%, and F-measure of 76.76\%. |
  - Problems and Issues in Parsing Manipuri Text - resource languages like Manipuri. |
  - A Grammar-Driven Approach for Parsing Manipuri Language - free grammar (CFG) and Earley’s parsing algorithm for parsing Manipuri language, achieving a Recall of 81.71\%, Precision of 72.38\%, and F-measure of 76.76\%. |
  - Problems and Issues in Parsing Manipuri Text - resource languages like Manipuri. |
  - A Grammar-Driven Approach for Parsing Manipuri Language - free grammar (CFG) and Earley’s parsing algorithm for parsing Manipuri language, achieving a Recall of 81.71\%, Precision of 72.38\%, and F-measure of 76.76\%. |
  - Problems and Issues in Parsing Manipuri Text - resource languages like Manipuri. |
  - A Grammar-Driven Approach for Parsing Manipuri Language - free grammar (CFG) and Earley’s parsing algorithm for parsing Manipuri language, achieving a Recall of 81.71\%, Precision of 72.38\%, and F-measure of 76.76\%. |
  - Problems and Issues in Parsing Manipuri Text - resource languages like Manipuri. |
  - A Grammar-Driven Approach for Parsing Manipuri Language - free grammar (CFG) and Earley’s parsing algorithm for parsing Manipuri language, achieving a Recall of 81.71\%, Precision of 72.38\%, and F-measure of 76.76\%. |
- Machine Translation
  - Statistical and Neural Machine Translation for Manipuri-English on Intelligence Domain - English machine translation system in an intelligence domain, utilizing 56,678 parallel corpora from open-source intelligence (OSINT) sources, with statistical machine translation (SMT) achieving a BLEU score of 23.91 and neural machine translation (NMT) outperforming with a BLEU score of 40.67. Additionally, language-specific morphological analysis, particularly focusing on suffixes, yields further improvements, with SMT achieving a BLEU score of 25.03 and NMT achieving a BLEU score of 44. |
  - An empirical study of low-resource neural machine translation of manipuri in multilingual settings - based neural machine translation system for Manipuri and English, incorporating cross-lingual features, which demonstrates improvement over vanilla multilingual and bilingual baselines, with enhanced performance across Manipuri-English and other Indian language-English translation tasks, including zero-shot translation evaluations. |
  - Low-Resource Indic Languages Translation Using Multilingual Approaches - trained transformers—mBART and mT5—on low-resource Indic languages, including Hindi, Bengali, Assamese, Manipuri, and Mizo, comparing their performance with multiway multilingual translation trained from scratch using a one-to-many and many-to-one approach, highlighting the scalability of multilingual neural machine translation (MNMT) and its potential for improving translation quality in low-resource language settings. |
  - Statistical and Neural Machine Translation for Manipuri-English on Intelligence Domain - English machine translation system in an intelligence domain, utilizing 56,678 parallel corpora from open-source intelligence (OSINT) sources, with statistical machine translation (SMT) achieving a BLEU score of 23.91 and neural machine translation (NMT) outperforming with a BLEU score of 40.67. Additionally, language-specific morphological analysis, particularly focusing on suffixes, yields further improvements, with SMT achieving a BLEU score of 25.03 and NMT achieving a BLEU score of 44. |
  - An empirical study of low-resource neural machine translation of manipuri in multilingual settings - based neural machine translation system for Manipuri and English, incorporating cross-lingual features, which demonstrates improvement over vanilla multilingual and bilingual baselines, with enhanced performance across Manipuri-English and other Indian language-English translation tasks, including zero-shot translation evaluations. |
  - An Exploratory Study of SMT Versus NMT for the Resource Constraint English to Manipuri Translation - to-Manipuri translation using BLEU, Meteor, TER, and F-measure scores as well as expert evaluation, to determine the most suitable approach for low-resource language pairs. |
  - Low-Resource Indic Languages Translation Using Multilingual Approaches - trained transformers—mBART and mT5—on low-resource Indic languages, including Hindi, Bengali, Assamese, Manipuri, and Mizo, comparing their performance with multiway multilingual translation trained from scratch using a one-to-many and many-to-one approach, highlighting the scalability of multilingual neural machine translation (MNMT) and its potential for improving translation quality in low-resource language settings. |
  - Statistical and Neural Machine Translation for Manipuri-English on Intelligence Domain - English machine translation system in an intelligence domain, utilizing 56,678 parallel corpora from open-source intelligence (OSINT) sources, with statistical machine translation (SMT) achieving a BLEU score of 23.91 and neural machine translation (NMT) outperforming with a BLEU score of 40.67. Additionally, language-specific morphological analysis, particularly focusing on suffixes, yields further improvements, with SMT achieving a BLEU score of 25.03 and NMT achieving a BLEU score of 44. |
  - An empirical study of low-resource neural machine translation of manipuri in multilingual settings - based neural machine translation system for Manipuri and English, incorporating cross-lingual features, which demonstrates improvement over vanilla multilingual and bilingual baselines, with enhanced performance across Manipuri-English and other Indian language-English translation tasks, including zero-shot translation evaluations. |
  - An Exploratory Study of SMT Versus NMT for the Resource Constraint English to Manipuri Translation - to-Manipuri translation using BLEU, Meteor, TER, and F-measure scores as well as expert evaluation, to determine the most suitable approach for low-resource language pairs. |
  - Low-Resource Indic Languages Translation Using Multilingual Approaches - trained transformers—mBART and mT5—on low-resource Indic languages, including Hindi, Bengali, Assamese, Manipuri, and Mizo, comparing their performance with multiway multilingual translation trained from scratch using a one-to-many and many-to-one approach, highlighting the scalability of multilingual neural machine translation (MNMT) and its potential for improving translation quality in low-resource language settings. |
  - Statistical and Neural Machine Translation for Manipuri-English on Intelligence Domain - English machine translation system in an intelligence domain, utilizing 56,678 parallel corpora from open-source intelligence (OSINT) sources, with statistical machine translation (SMT) achieving a BLEU score of 23.91 and neural machine translation (NMT) outperforming with a BLEU score of 40.67. Additionally, language-specific morphological analysis, particularly focusing on suffixes, yields further improvements, with SMT achieving a BLEU score of 25.03 and NMT achieving a BLEU score of 44. |
  - An empirical study of low-resource neural machine translation of manipuri in multilingual settings - based neural machine translation system for Manipuri and English, incorporating cross-lingual features, which demonstrates improvement over vanilla multilingual and bilingual baselines, with enhanced performance across Manipuri-English and other Indian language-English translation tasks, including zero-shot translation evaluations. |
  - An Exploratory Study of SMT Versus NMT for the Resource Constraint English to Manipuri Translation - to-Manipuri translation using BLEU, Meteor, TER, and F-measure scores as well as expert evaluation, to determine the most suitable approach for low-resource language pairs. |
  - Low-Resource Indic Languages Translation Using Multilingual Approaches - trained transformers—mBART and mT5—on low-resource Indic languages, including Hindi, Bengali, Assamese, Manipuri, and Mizo, comparing their performance with multiway multilingual translation trained from scratch using a one-to-many and many-to-one approach, highlighting the scalability of multilingual neural machine translation (MNMT) and its potential for improving translation quality in low-resource language settings. |
  - Statistical and Neural Machine Translation for Manipuri-English on Intelligence Domain - English machine translation system in an intelligence domain, utilizing 56,678 parallel corpora from open-source intelligence (OSINT) sources, with statistical machine translation (SMT) achieving a BLEU score of 23.91 and neural machine translation (NMT) outperforming with a BLEU score of 40.67. Additionally, language-specific morphological analysis, particularly focusing on suffixes, yields further improvements, with SMT achieving a BLEU score of 25.03 and NMT achieving a BLEU score of 44. |
  - An empirical study of low-resource neural machine translation of manipuri in multilingual settings - based neural machine translation system for Manipuri and English, incorporating cross-lingual features, which demonstrates improvement over vanilla multilingual and bilingual baselines, with enhanced performance across Manipuri-English and other Indian language-English translation tasks, including zero-shot translation evaluations. |
  - An Exploratory Study of SMT Versus NMT for the Resource Constraint English to Manipuri Translation - to-Manipuri translation using BLEU, Meteor, TER, and F-measure scores as well as expert evaluation, to determine the most suitable approach for low-resource language pairs. |
  - Low-Resource Indic Languages Translation Using Multilingual Approaches - trained transformers—mBART and mT5—on low-resource Indic languages, including Hindi, Bengali, Assamese, Manipuri, and Mizo, comparing their performance with multiway multilingual translation trained from scratch using a one-to-many and many-to-one approach, highlighting the scalability of multilingual neural machine translation (MNMT) and its potential for improving translation quality in low-resource language settings. |
  - Statistical and Neural Machine Translation for Manipuri-English on Intelligence Domain - English machine translation system in an intelligence domain, utilizing 56,678 parallel corpora from open-source intelligence (OSINT) sources, with statistical machine translation (SMT) achieving a BLEU score of 23.91 and neural machine translation (NMT) outperforming with a BLEU score of 40.67. Additionally, language-specific morphological analysis, particularly focusing on suffixes, yields further improvements, with SMT achieving a BLEU score of 25.03 and NMT achieving a BLEU score of 44. |
  - An empirical study of low-resource neural machine translation of manipuri in multilingual settings - based neural machine translation system for Manipuri and English, incorporating cross-lingual features, which demonstrates improvement over vanilla multilingual and bilingual baselines, with enhanced performance across Manipuri-English and other Indian language-English translation tasks, including zero-shot translation evaluations. |
  - An Exploratory Study of SMT Versus NMT for the Resource Constraint English to Manipuri Translation - to-Manipuri translation using BLEU, Meteor, TER, and F-measure scores as well as expert evaluation, to determine the most suitable approach for low-resource language pairs. |
  - Low-Resource Indic Languages Translation Using Multilingual Approaches - trained transformers—mBART and mT5—on low-resource Indic languages, including Hindi, Bengali, Assamese, Manipuri, and Mizo, comparing their performance with multiway multilingual translation trained from scratch using a one-to-many and many-to-one approach, highlighting the scalability of multilingual neural machine translation (MNMT) and its potential for improving translation quality in low-resource language settings. |
  - Statistical and Neural Machine Translation for Manipuri-English on Intelligence Domain - English machine translation system in an intelligence domain, utilizing 56,678 parallel corpora from open-source intelligence (OSINT) sources, with statistical machine translation (SMT) achieving a BLEU score of 23.91 and neural machine translation (NMT) outperforming with a BLEU score of 40.67. Additionally, language-specific morphological analysis, particularly focusing on suffixes, yields further improvements, with SMT achieving a BLEU score of 25.03 and NMT achieving a BLEU score of 44. |
  - Unsupervised Neural Machine Translation for English and Manipuri - resource English-Manipuri language pair, achieving BLEU scores of 3.1 for en → mni and 2.7 for mni → en translations, with subjective evaluation yielding encouraging results on the translated output. |
  - Statistical and Neural Machine Translation for Manipuri-English on Intelligence Domain - English machine translation system in an intelligence domain, utilizing 56,678 parallel corpora from open-source intelligence (OSINT) sources, with statistical machine translation (SMT) achieving a BLEU score of 23.91 and neural machine translation (NMT) outperforming with a BLEU score of 40.67. Additionally, language-specific morphological analysis, particularly focusing on suffixes, yields further improvements, with SMT achieving a BLEU score of 25.03 and NMT achieving a BLEU score of 44. |
  - An empirical study of low-resource neural machine translation of manipuri in multilingual settings - based neural machine translation system for Manipuri and English, incorporating cross-lingual features, which demonstrates improvement over vanilla multilingual and bilingual baselines, with enhanced performance across Manipuri-English and other Indian language-English translation tasks, including zero-shot translation evaluations. |
  - An Exploratory Study of SMT Versus NMT for the Resource Constraint English to Manipuri Translation - to-Manipuri translation using BLEU, Meteor, TER, and F-measure scores as well as expert evaluation, to determine the most suitable approach for low-resource language pairs. |
  - An empirical study of low-resource neural machine translation of manipuri in multilingual settings - based neural machine translation system for Manipuri and English, incorporating cross-lingual features, which demonstrates improvement over vanilla multilingual and bilingual baselines, with enhanced performance across Manipuri-English and other Indian language-English translation tasks, including zero-shot translation evaluations. |
  - An Exploratory Study of SMT Versus NMT for the Resource Constraint English to Manipuri Translation - to-Manipuri translation using BLEU, Meteor, TER, and F-measure scores as well as expert evaluation, to determine the most suitable approach for low-resource language pairs. |
  - Low-Resource Indic Languages Translation Using Multilingual Approaches - trained transformers—mBART and mT5—on low-resource Indic languages, including Hindi, Bengali, Assamese, Manipuri, and Mizo, comparing their performance with multiway multilingual translation trained from scratch using a one-to-many and many-to-one approach, highlighting the scalability of multilingual neural machine translation (MNMT) and its potential for improving translation quality in low-resource language settings. |
  - Low-Resource Indic Languages Translation Using Multilingual Approaches - trained transformers—mBART and mT5—on low-resource Indic languages, including Hindi, Bengali, Assamese, Manipuri, and Mizo, comparing their performance with multiway multilingual translation trained from scratch using a one-to-many and many-to-one approach, highlighting the scalability of multilingual neural machine translation (MNMT) and its potential for improving translation quality in low-resource language settings. |
  - Statistical and Neural Machine Translation for Manipuri-English on Intelligence Domain - English machine translation system in an intelligence domain, utilizing 56,678 parallel corpora from open-source intelligence (OSINT) sources, with statistical machine translation (SMT) achieving a BLEU score of 23.91 and neural machine translation (NMT) outperforming with a BLEU score of 40.67. Additionally, language-specific morphological analysis, particularly focusing on suffixes, yields further improvements, with SMT achieving a BLEU score of 25.03 and NMT achieving a BLEU score of 44. |
  - An Exploratory Study of SMT Versus NMT for the Resource Constraint English to Manipuri Translation - to-Manipuri translation using BLEU, Meteor, TER, and F-measure scores as well as expert evaluation, to determine the most suitable approach for low-resource language pairs. |
  - Statistical and Neural Machine Translation for Manipuri-English on Intelligence Domain - English machine translation system in an intelligence domain, utilizing 56,678 parallel corpora from open-source intelligence (OSINT) sources, with statistical machine translation (SMT) achieving a BLEU score of 23.91 and neural machine translation (NMT) outperforming with a BLEU score of 40.67. Additionally, language-specific morphological analysis, particularly focusing on suffixes, yields further improvements, with SMT achieving a BLEU score of 25.03 and NMT achieving a BLEU score of 44. |
  - An empirical study of low-resource neural machine translation of manipuri in multilingual settings - based neural machine translation system for Manipuri and English, incorporating cross-lingual features, which demonstrates improvement over vanilla multilingual and bilingual baselines, with enhanced performance across Manipuri-English and other Indian language-English translation tasks, including zero-shot translation evaluations. |
  - Low-Resource Indic Languages Translation Using Multilingual Approaches - trained transformers—mBART and mT5—on low-resource Indic languages, including Hindi, Bengali, Assamese, Manipuri, and Mizo, comparing their performance with multiway multilingual translation trained from scratch using a one-to-many and many-to-one approach, highlighting the scalability of multilingual neural machine translation (MNMT) and its potential for improving translation quality in low-resource language settings. |
  - Low-Resource Indic Languages Translation Using Multilingual Approaches - trained transformers—mBART and mT5—on low-resource Indic languages, including Hindi, Bengali, Assamese, Manipuri, and Mizo, comparing their performance with multiway multilingual translation trained from scratch using a one-to-many and many-to-one approach, highlighting the scalability of multilingual neural machine translation (MNMT) and its potential for improving translation quality in low-resource language settings. |
  - An empirical study of low-resource neural machine translation of manipuri in multilingual settings - based neural machine translation system for Manipuri and English, incorporating cross-lingual features, which demonstrates improvement over vanilla multilingual and bilingual baselines, with enhanced performance across Manipuri-English and other Indian language-English translation tasks, including zero-shot translation evaluations. |
  - An Exploratory Study of SMT Versus NMT for the Resource Constraint English to Manipuri Translation - to-Manipuri translation using BLEU, Meteor, TER, and F-measure scores as well as expert evaluation, to determine the most suitable approach for low-resource language pairs. |
  - Statistical and Neural Machine Translation for Manipuri-English on Intelligence Domain - English machine translation system in an intelligence domain, utilizing 56,678 parallel corpora from open-source intelligence (OSINT) sources, with statistical machine translation (SMT) achieving a BLEU score of 23.91 and neural machine translation (NMT) outperforming with a BLEU score of 40.67. Additionally, language-specific morphological analysis, particularly focusing on suffixes, yields further improvements, with SMT achieving a BLEU score of 25.03 and NMT achieving a BLEU score of 44. |
  - An empirical study of low-resource neural machine translation of manipuri in multilingual settings - based neural machine translation system for Manipuri and English, incorporating cross-lingual features, which demonstrates improvement over vanilla multilingual and bilingual baselines, with enhanced performance across Manipuri-English and other Indian language-English translation tasks, including zero-shot translation evaluations. |
  - An Exploratory Study of SMT Versus NMT for the Resource Constraint English to Manipuri Translation - to-Manipuri translation using BLEU, Meteor, TER, and F-measure scores as well as expert evaluation, to determine the most suitable approach for low-resource language pairs. |
  - Low-Resource Indic Languages Translation Using Multilingual Approaches - trained transformers—mBART and mT5—on low-resource Indic languages, including Hindi, Bengali, Assamese, Manipuri, and Mizo, comparing their performance with multiway multilingual translation trained from scratch using a one-to-many and many-to-one approach, highlighting the scalability of multilingual neural machine translation (MNMT) and its potential for improving translation quality in low-resource language settings. |
  - Statistical and Neural Machine Translation for Manipuri-English on Intelligence Domain - English machine translation system in an intelligence domain, utilizing 56,678 parallel corpora from open-source intelligence (OSINT) sources, with statistical machine translation (SMT) achieving a BLEU score of 23.91 and neural machine translation (NMT) outperforming with a BLEU score of 40.67. Additionally, language-specific morphological analysis, particularly focusing on suffixes, yields further improvements, with SMT achieving a BLEU score of 25.03 and NMT achieving a BLEU score of 44. |
  - An empirical study of low-resource neural machine translation of manipuri in multilingual settings - based neural machine translation system for Manipuri and English, incorporating cross-lingual features, which demonstrates improvement over vanilla multilingual and bilingual baselines, with enhanced performance across Manipuri-English and other Indian language-English translation tasks, including zero-shot translation evaluations. |
  - Low-Resource Indic Languages Translation Using Multilingual Approaches - trained transformers—mBART and mT5—on low-resource Indic languages, including Hindi, Bengali, Assamese, Manipuri, and Mizo, comparing their performance with multiway multilingual translation trained from scratch using a one-to-many and many-to-one approach, highlighting the scalability of multilingual neural machine translation (MNMT) and its potential for improving translation quality in low-resource language settings. |
  - Statistical and Neural Machine Translation for Manipuri-English on Intelligence Domain - English machine translation system in an intelligence domain, utilizing 56,678 parallel corpora from open-source intelligence (OSINT) sources, with statistical machine translation (SMT) achieving a BLEU score of 23.91 and neural machine translation (NMT) outperforming with a BLEU score of 40.67. Additionally, language-specific morphological analysis, particularly focusing on suffixes, yields further improvements, with SMT achieving a BLEU score of 25.03 and NMT achieving a BLEU score of 44. |
  - An empirical study of low-resource neural machine translation of manipuri in multilingual settings - based neural machine translation system for Manipuri and English, incorporating cross-lingual features, which demonstrates improvement over vanilla multilingual and bilingual baselines, with enhanced performance across Manipuri-English and other Indian language-English translation tasks, including zero-shot translation evaluations. |
  - An Exploratory Study of SMT Versus NMT for the Resource Constraint English to Manipuri Translation - to-Manipuri translation using BLEU, Meteor, TER, and F-measure scores as well as expert evaluation, to determine the most suitable approach for low-resource language pairs. |
  - Low-Resource Indic Languages Translation Using Multilingual Approaches - trained transformers—mBART and mT5—on low-resource Indic languages, including Hindi, Bengali, Assamese, Manipuri, and Mizo, comparing their performance with multiway multilingual translation trained from scratch using a one-to-many and many-to-one approach, highlighting the scalability of multilingual neural machine translation (MNMT) and its potential for improving translation quality in low-resource language settings. |
  - Low-Resource Indic Languages Translation Using Multilingual Approaches - trained transformers—mBART and mT5—on low-resource Indic languages, including Hindi, Bengali, Assamese, Manipuri, and Mizo, comparing their performance with multiway multilingual translation trained from scratch using a one-to-many and many-to-one approach, highlighting the scalability of multilingual neural machine translation (MNMT) and its potential for improving translation quality in low-resource language settings. |
  - Statistical and Neural Machine Translation for Manipuri-English on Intelligence Domain - English machine translation system in an intelligence domain, utilizing 56,678 parallel corpora from open-source intelligence (OSINT) sources, with statistical machine translation (SMT) achieving a BLEU score of 23.91 and neural machine translation (NMT) outperforming with a BLEU score of 40.67. Additionally, language-specific morphological analysis, particularly focusing on suffixes, yields further improvements, with SMT achieving a BLEU score of 25.03 and NMT achieving a BLEU score of 44. |
  - An empirical study of low-resource neural machine translation of manipuri in multilingual settings - based neural machine translation system for Manipuri and English, incorporating cross-lingual features, which demonstrates improvement over vanilla multilingual and bilingual baselines, with enhanced performance across Manipuri-English and other Indian language-English translation tasks, including zero-shot translation evaluations. |
  - An Exploratory Study of SMT Versus NMT for the Resource Constraint English to Manipuri Translation - to-Manipuri translation using BLEU, Meteor, TER, and F-measure scores as well as expert evaluation, to determine the most suitable approach for low-resource language pairs. |
  - Statistical and Neural Machine Translation for Manipuri-English on Intelligence Domain - English machine translation system in an intelligence domain, utilizing 56,678 parallel corpora from open-source intelligence (OSINT) sources, with statistical machine translation (SMT) achieving a BLEU score of 23.91 and neural machine translation (NMT) outperforming with a BLEU score of 40.67. Additionally, language-specific morphological analysis, particularly focusing on suffixes, yields further improvements, with SMT achieving a BLEU score of 25.03 and NMT achieving a BLEU score of 44. |
  - An empirical study of low-resource neural machine translation of manipuri in multilingual settings - based neural machine translation system for Manipuri and English, incorporating cross-lingual features, which demonstrates improvement over vanilla multilingual and bilingual baselines, with enhanced performance across Manipuri-English and other Indian language-English translation tasks, including zero-shot translation evaluations. |
  - An Exploratory Study of SMT Versus NMT for the Resource Constraint English to Manipuri Translation - to-Manipuri translation using BLEU, Meteor, TER, and F-measure scores as well as expert evaluation, to determine the most suitable approach for low-resource language pairs. |
  - Low-Resource Indic Languages Translation Using Multilingual Approaches - trained transformers—mBART and mT5—on low-resource Indic languages, including Hindi, Bengali, Assamese, Manipuri, and Mizo, comparing their performance with multiway multilingual translation trained from scratch using a one-to-many and many-to-one approach, highlighting the scalability of multilingual neural machine translation (MNMT) and its potential for improving translation quality in low-resource language settings. |
  - Statistical and Neural Machine Translation for Manipuri-English on Intelligence Domain - English machine translation system in an intelligence domain, utilizing 56,678 parallel corpora from open-source intelligence (OSINT) sources, with statistical machine translation (SMT) achieving a BLEU score of 23.91 and neural machine translation (NMT) outperforming with a BLEU score of 40.67. Additionally, language-specific morphological analysis, particularly focusing on suffixes, yields further improvements, with SMT achieving a BLEU score of 25.03 and NMT achieving a BLEU score of 44. |
  - An empirical study of low-resource neural machine translation of manipuri in multilingual settings - based neural machine translation system for Manipuri and English, incorporating cross-lingual features, which demonstrates improvement over vanilla multilingual and bilingual baselines, with enhanced performance across Manipuri-English and other Indian language-English translation tasks, including zero-shot translation evaluations. |
  - An Exploratory Study of SMT Versus NMT for the Resource Constraint English to Manipuri Translation - to-Manipuri translation using BLEU, Meteor, TER, and F-measure scores as well as expert evaluation, to determine the most suitable approach for low-resource language pairs. |
  - Low-Resource Indic Languages Translation Using Multilingual Approaches - trained transformers—mBART and mT5—on low-resource Indic languages, including Hindi, Bengali, Assamese, Manipuri, and Mizo, comparing their performance with multiway multilingual translation trained from scratch using a one-to-many and many-to-one approach, highlighting the scalability of multilingual neural machine translation (MNMT) and its potential for improving translation quality in low-resource language settings. |
  - Statistical and Neural Machine Translation for Manipuri-English on Intelligence Domain - English machine translation system in an intelligence domain, utilizing 56,678 parallel corpora from open-source intelligence (OSINT) sources, with statistical machine translation (SMT) achieving a BLEU score of 23.91 and neural machine translation (NMT) outperforming with a BLEU score of 40.67. Additionally, language-specific morphological analysis, particularly focusing on suffixes, yields further improvements, with SMT achieving a BLEU score of 25.03 and NMT achieving a BLEU score of 44. |
  - An empirical study of low-resource neural machine translation of manipuri in multilingual settings - based neural machine translation system for Manipuri and English, incorporating cross-lingual features, which demonstrates improvement over vanilla multilingual and bilingual baselines, with enhanced performance across Manipuri-English and other Indian language-English translation tasks, including zero-shot translation evaluations. |
  - An Exploratory Study of SMT Versus NMT for the Resource Constraint English to Manipuri Translation - to-Manipuri translation using BLEU, Meteor, TER, and F-measure scores as well as expert evaluation, to determine the most suitable approach for low-resource language pairs. |
  - Low-Resource Indic Languages Translation Using Multilingual Approaches - trained transformers—mBART and mT5—on low-resource Indic languages, including Hindi, Bengali, Assamese, Manipuri, and Mizo, comparing their performance with multiway multilingual translation trained from scratch using a one-to-many and many-to-one approach, highlighting the scalability of multilingual neural machine translation (MNMT) and its potential for improving translation quality in low-resource language settings. |
  - Statistical and Neural Machine Translation for Manipuri-English on Intelligence Domain - English machine translation system in an intelligence domain, utilizing 56,678 parallel corpora from open-source intelligence (OSINT) sources, with statistical machine translation (SMT) achieving a BLEU score of 23.91 and neural machine translation (NMT) outperforming with a BLEU score of 40.67. Additionally, language-specific morphological analysis, particularly focusing on suffixes, yields further improvements, with SMT achieving a BLEU score of 25.03 and NMT achieving a BLEU score of 44. |
  - An empirical study of low-resource neural machine translation of manipuri in multilingual settings - based neural machine translation system for Manipuri and English, incorporating cross-lingual features, which demonstrates improvement over vanilla multilingual and bilingual baselines, with enhanced performance across Manipuri-English and other Indian language-English translation tasks, including zero-shot translation evaluations. |
  - An Exploratory Study of SMT Versus NMT for the Resource Constraint English to Manipuri Translation - to-Manipuri translation using BLEU, Meteor, TER, and F-measure scores as well as expert evaluation, to determine the most suitable approach for low-resource language pairs. |
  - Low-Resource Indic Languages Translation Using Multilingual Approaches - trained transformers—mBART and mT5—on low-resource Indic languages, including Hindi, Bengali, Assamese, Manipuri, and Mizo, comparing their performance with multiway multilingual translation trained from scratch using a one-to-many and many-to-one approach, highlighting the scalability of multilingual neural machine translation (MNMT) and its potential for improving translation quality in low-resource language settings. |
  - Statistical and Neural Machine Translation for Manipuri-English on Intelligence Domain - English machine translation system in an intelligence domain, utilizing 56,678 parallel corpora from open-source intelligence (OSINT) sources, with statistical machine translation (SMT) achieving a BLEU score of 23.91 and neural machine translation (NMT) outperforming with a BLEU score of 40.67. Additionally, language-specific morphological analysis, particularly focusing on suffixes, yields further improvements, with SMT achieving a BLEU score of 25.03 and NMT achieving a BLEU score of 44. |
  - An empirical study of low-resource neural machine translation of manipuri in multilingual settings - based neural machine translation system for Manipuri and English, incorporating cross-lingual features, which demonstrates improvement over vanilla multilingual and bilingual baselines, with enhanced performance across Manipuri-English and other Indian language-English translation tasks, including zero-shot translation evaluations. |
  - An Exploratory Study of SMT Versus NMT for the Resource Constraint English to Manipuri Translation - to-Manipuri translation using BLEU, Meteor, TER, and F-measure scores as well as expert evaluation, to determine the most suitable approach for low-resource language pairs. |
  - Low-Resource Indic Languages Translation Using Multilingual Approaches - trained transformers—mBART and mT5—on low-resource Indic languages, including Hindi, Bengali, Assamese, Manipuri, and Mizo, comparing their performance with multiway multilingual translation trained from scratch using a one-to-many and many-to-one approach, highlighting the scalability of multilingual neural machine translation (MNMT) and its potential for improving translation quality in low-resource language settings. |
  - An Exploratory Study of SMT Versus NMT for the Resource Constraint English to Manipuri Translation - to-Manipuri translation using BLEU, Meteor, TER, and F-measure scores as well as expert evaluation, to determine the most suitable approach for low-resource language pairs. |
  - Low-Resource Indic Languages Translation Using Multilingual Approaches - trained transformers—mBART and mT5—on low-resource Indic languages, including Hindi, Bengali, Assamese, Manipuri, and Mizo, comparing their performance with multiway multilingual translation trained from scratch using a one-to-many and many-to-one approach, highlighting the scalability of multilingual neural machine translation (MNMT) and its potential for improving translation quality in low-resource language settings. |
  - Statistical and Neural Machine Translation for Manipuri-English on Intelligence Domain - English machine translation system in an intelligence domain, utilizing 56,678 parallel corpora from open-source intelligence (OSINT) sources, with statistical machine translation (SMT) achieving a BLEU score of 23.91 and neural machine translation (NMT) outperforming with a BLEU score of 40.67. Additionally, language-specific morphological analysis, particularly focusing on suffixes, yields further improvements, with SMT achieving a BLEU score of 25.03 and NMT achieving a BLEU score of 44. |
  - An empirical study of low-resource neural machine translation of manipuri in multilingual settings - based neural machine translation system for Manipuri and English, incorporating cross-lingual features, which demonstrates improvement over vanilla multilingual and bilingual baselines, with enhanced performance across Manipuri-English and other Indian language-English translation tasks, including zero-shot translation evaluations. |
  - Statistical and Neural Machine Translation for Manipuri-English on Intelligence Domain - English machine translation system in an intelligence domain, utilizing 56,678 parallel corpora from open-source intelligence (OSINT) sources, with statistical machine translation (SMT) achieving a BLEU score of 23.91 and neural machine translation (NMT) outperforming with a BLEU score of 40.67. Additionally, language-specific morphological analysis, particularly focusing on suffixes, yields further improvements, with SMT achieving a BLEU score of 25.03 and NMT achieving a BLEU score of 44. |
  - An empirical study of low-resource neural machine translation of manipuri in multilingual settings - based neural machine translation system for Manipuri and English, incorporating cross-lingual features, which demonstrates improvement over vanilla multilingual and bilingual baselines, with enhanced performance across Manipuri-English and other Indian language-English translation tasks, including zero-shot translation evaluations. |
  - An Exploratory Study of SMT Versus NMT for the Resource Constraint English to Manipuri Translation - to-Manipuri translation using BLEU, Meteor, TER, and F-measure scores as well as expert evaluation, to determine the most suitable approach for low-resource language pairs. |
  - Low-Resource Indic Languages Translation Using Multilingual Approaches - trained transformers—mBART and mT5—on low-resource Indic languages, including Hindi, Bengali, Assamese, Manipuri, and Mizo, comparing their performance with multiway multilingual translation trained from scratch using a one-to-many and many-to-one approach, highlighting the scalability of multilingual neural machine translation (MNMT) and its potential for improving translation quality in low-resource language settings. |
  - Low-Resource Indic Languages Translation Using Multilingual Approaches - trained transformers—mBART and mT5—on low-resource Indic languages, including Hindi, Bengali, Assamese, Manipuri, and Mizo, comparing their performance with multiway multilingual translation trained from scratch using a one-to-many and many-to-one approach, highlighting the scalability of multilingual neural machine translation (MNMT) and its potential for improving translation quality in low-resource language settings. |
  - Statistical and Neural Machine Translation for Manipuri-English on Intelligence Domain - English machine translation system in an intelligence domain, utilizing 56,678 parallel corpora from open-source intelligence (OSINT) sources, with statistical machine translation (SMT) achieving a BLEU score of 23.91 and neural machine translation (NMT) outperforming with a BLEU score of 40.67. Additionally, language-specific morphological analysis, particularly focusing on suffixes, yields further improvements, with SMT achieving a BLEU score of 25.03 and NMT achieving a BLEU score of 44. |
  - An empirical study of low-resource neural machine translation of manipuri in multilingual settings - based neural machine translation system for Manipuri and English, incorporating cross-lingual features, which demonstrates improvement over vanilla multilingual and bilingual baselines, with enhanced performance across Manipuri-English and other Indian language-English translation tasks, including zero-shot translation evaluations. |
  - An Exploratory Study of SMT Versus NMT for the Resource Constraint English to Manipuri Translation - to-Manipuri translation using BLEU, Meteor, TER, and F-measure scores as well as expert evaluation, to determine the most suitable approach for low-resource language pairs. |
  - An Exploratory Study of SMT Versus NMT for the Resource Constraint English to Manipuri Translation - to-Manipuri translation using BLEU, Meteor, TER, and F-measure scores as well as expert evaluation, to determine the most suitable approach for low-resource language pairs. |
  - Statistical and Neural Machine Translation for Manipuri-English on Intelligence Domain - English machine translation system in an intelligence domain, utilizing 56,678 parallel corpora from open-source intelligence (OSINT) sources, with statistical machine translation (SMT) achieving a BLEU score of 23.91 and neural machine translation (NMT) outperforming with a BLEU score of 40.67. Additionally, language-specific morphological analysis, particularly focusing on suffixes, yields further improvements, with SMT achieving a BLEU score of 25.03 and NMT achieving a BLEU score of 44. |
  - An empirical study of low-resource neural machine translation of manipuri in multilingual settings - based neural machine translation system for Manipuri and English, incorporating cross-lingual features, which demonstrates improvement over vanilla multilingual and bilingual baselines, with enhanced performance across Manipuri-English and other Indian language-English translation tasks, including zero-shot translation evaluations. |
  - Low-Resource Indic Languages Translation Using Multilingual Approaches - trained transformers—mBART and mT5—on low-resource Indic languages, including Hindi, Bengali, Assamese, Manipuri, and Mizo, comparing their performance with multiway multilingual translation trained from scratch using a one-to-many and many-to-one approach, highlighting the scalability of multilingual neural machine translation (MNMT) and its potential for improving translation quality in low-resource language settings. |
  - An Exploratory Study of SMT Versus NMT for the Resource Constraint English to Manipuri Translation - to-Manipuri translation using BLEU, Meteor, TER, and F-measure scores as well as expert evaluation, to determine the most suitable approach for low-resource language pairs. |
  - Statistical and Neural Machine Translation for Manipuri-English on Intelligence Domain - English machine translation system in an intelligence domain, utilizing 56,678 parallel corpora from open-source intelligence (OSINT) sources, with statistical machine translation (SMT) achieving a BLEU score of 23.91 and neural machine translation (NMT) outperforming with a BLEU score of 40.67. Additionally, language-specific morphological analysis, particularly focusing on suffixes, yields further improvements, with SMT achieving a BLEU score of 25.03 and NMT achieving a BLEU score of 44. |
  - An empirical study of low-resource neural machine translation of manipuri in multilingual settings - based neural machine translation system for Manipuri and English, incorporating cross-lingual features, which demonstrates improvement over vanilla multilingual and bilingual baselines, with enhanced performance across Manipuri-English and other Indian language-English translation tasks, including zero-shot translation evaluations. |
  - Low-Resource Indic Languages Translation Using Multilingual Approaches - trained transformers—mBART and mT5—on low-resource Indic languages, including Hindi, Bengali, Assamese, Manipuri, and Mizo, comparing their performance with multiway multilingual translation trained from scratch using a one-to-many and many-to-one approach, highlighting the scalability of multilingual neural machine translation (MNMT) and its potential for improving translation quality in low-resource language settings. |
  - Statistical and Neural Machine Translation for Manipuri-English on Intelligence Domain - English machine translation system in an intelligence domain, utilizing 56,678 parallel corpora from open-source intelligence (OSINT) sources, with statistical machine translation (SMT) achieving a BLEU score of 23.91 and neural machine translation (NMT) outperforming with a BLEU score of 40.67. Additionally, language-specific morphological analysis, particularly focusing on suffixes, yields further improvements, with SMT achieving a BLEU score of 25.03 and NMT achieving a BLEU score of 44. |
  - An empirical study of low-resource neural machine translation of manipuri in multilingual settings - based neural machine translation system for Manipuri and English, incorporating cross-lingual features, which demonstrates improvement over vanilla multilingual and bilingual baselines, with enhanced performance across Manipuri-English and other Indian language-English translation tasks, including zero-shot translation evaluations. |
  - An Exploratory Study of SMT Versus NMT for the Resource Constraint English to Manipuri Translation - to-Manipuri translation using BLEU, Meteor, TER, and F-measure scores as well as expert evaluation, to determine the most suitable approach for low-resource language pairs. |
  - Low-Resource Indic Languages Translation Using Multilingual Approaches - trained transformers—mBART and mT5—on low-resource Indic languages, including Hindi, Bengali, Assamese, Manipuri, and Mizo, comparing their performance with multiway multilingual translation trained from scratch using a one-to-many and many-to-one approach, highlighting the scalability of multilingual neural machine translation (MNMT) and its potential for improving translation quality in low-resource language settings. |
  - Statistical and Neural Machine Translation for Manipuri-English on Intelligence Domain - English machine translation system in an intelligence domain, utilizing 56,678 parallel corpora from open-source intelligence (OSINT) sources, with statistical machine translation (SMT) achieving a BLEU score of 23.91 and neural machine translation (NMT) outperforming with a BLEU score of 40.67. Additionally, language-specific morphological analysis, particularly focusing on suffixes, yields further improvements, with SMT achieving a BLEU score of 25.03 and NMT achieving a BLEU score of 44. |
  - An empirical study of low-resource neural machine translation of manipuri in multilingual settings - based neural machine translation system for Manipuri and English, incorporating cross-lingual features, which demonstrates improvement over vanilla multilingual and bilingual baselines, with enhanced performance across Manipuri-English and other Indian language-English translation tasks, including zero-shot translation evaluations. |
  - An Exploratory Study of SMT Versus NMT for the Resource Constraint English to Manipuri Translation - to-Manipuri translation using BLEU, Meteor, TER, and F-measure scores as well as expert evaluation, to determine the most suitable approach for low-resource language pairs. |
  - Low-Resource Indic Languages Translation Using Multilingual Approaches - trained transformers—mBART and mT5—on low-resource Indic languages, including Hindi, Bengali, Assamese, Manipuri, and Mizo, comparing their performance with multiway multilingual translation trained from scratch using a one-to-many and many-to-one approach, highlighting the scalability of multilingual neural machine translation (MNMT) and its potential for improving translation quality in low-resource language settings. |
  - Statistical and Neural Machine Translation for Manipuri-English on Intelligence Domain - English machine translation system in an intelligence domain, utilizing 56,678 parallel corpora from open-source intelligence (OSINT) sources, with statistical machine translation (SMT) achieving a BLEU score of 23.91 and neural machine translation (NMT) outperforming with a BLEU score of 40.67. Additionally, language-specific morphological analysis, particularly focusing on suffixes, yields further improvements, with SMT achieving a BLEU score of 25.03 and NMT achieving a BLEU score of 44. |
  - An empirical study of low-resource neural machine translation of manipuri in multilingual settings - based neural machine translation system for Manipuri and English, incorporating cross-lingual features, which demonstrates improvement over vanilla multilingual and bilingual baselines, with enhanced performance across Manipuri-English and other Indian language-English translation tasks, including zero-shot translation evaluations. |
  - An Exploratory Study of SMT Versus NMT for the Resource Constraint English to Manipuri Translation - to-Manipuri translation using BLEU, Meteor, TER, and F-measure scores as well as expert evaluation, to determine the most suitable approach for low-resource language pairs. |
  - Low-Resource Indic Languages Translation Using Multilingual Approaches - trained transformers—mBART and mT5—on low-resource Indic languages, including Hindi, Bengali, Assamese, Manipuri, and Mizo, comparing their performance with multiway multilingual translation trained from scratch using a one-to-many and many-to-one approach, highlighting the scalability of multilingual neural machine translation (MNMT) and its potential for improving translation quality in low-resource language settings. |
  - Statistical and Neural Machine Translation for Manipuri-English on Intelligence Domain - English machine translation system in an intelligence domain, utilizing 56,678 parallel corpora from open-source intelligence (OSINT) sources, with statistical machine translation (SMT) achieving a BLEU score of 23.91 and neural machine translation (NMT) outperforming with a BLEU score of 40.67. Additionally, language-specific morphological analysis, particularly focusing on suffixes, yields further improvements, with SMT achieving a BLEU score of 25.03 and NMT achieving a BLEU score of 44. |
  - Low-Resource Indic Languages Translation Using Multilingual Approaches - trained transformers—mBART and mT5—on low-resource Indic languages, including Hindi, Bengali, Assamese, Manipuri, and Mizo, comparing their performance with multiway multilingual translation trained from scratch using a one-to-many and many-to-one approach, highlighting the scalability of multilingual neural machine translation (MNMT) and its potential for improving translation quality in low-resource language settings. |
  - An empirical study of low-resource neural machine translation of manipuri in multilingual settings - based neural machine translation system for Manipuri and English, incorporating cross-lingual features, which demonstrates improvement over vanilla multilingual and bilingual baselines, with enhanced performance across Manipuri-English and other Indian language-English translation tasks, including zero-shot translation evaluations. |
  - An Exploratory Study of SMT Versus NMT for the Resource Constraint English to Manipuri Translation - to-Manipuri translation using BLEU, Meteor, TER, and F-measure scores as well as expert evaluation, to determine the most suitable approach for low-resource language pairs. |
  - Statistical and Neural Machine Translation for Manipuri-English on Intelligence Domain - English machine translation system in an intelligence domain, utilizing 56,678 parallel corpora from open-source intelligence (OSINT) sources, with statistical machine translation (SMT) achieving a BLEU score of 23.91 and neural machine translation (NMT) outperforming with a BLEU score of 40.67. Additionally, language-specific morphological analysis, particularly focusing on suffixes, yields further improvements, with SMT achieving a BLEU score of 25.03 and NMT achieving a BLEU score of 44. |
  - An empirical study of low-resource neural machine translation of manipuri in multilingual settings - based neural machine translation system for Manipuri and English, incorporating cross-lingual features, which demonstrates improvement over vanilla multilingual and bilingual baselines, with enhanced performance across Manipuri-English and other Indian language-English translation tasks, including zero-shot translation evaluations. |
  - Low-Resource Indic Languages Translation Using Multilingual Approaches - trained transformers—mBART and mT5—on low-resource Indic languages, including Hindi, Bengali, Assamese, Manipuri, and Mizo, comparing their performance with multiway multilingual translation trained from scratch using a one-to-many and many-to-one approach, highlighting the scalability of multilingual neural machine translation (MNMT) and its potential for improving translation quality in low-resource language settings. |
  - Statistical and Neural Machine Translation for Manipuri-English on Intelligence Domain - English machine translation system in an intelligence domain, utilizing 56,678 parallel corpora from open-source intelligence (OSINT) sources, with statistical machine translation (SMT) achieving a BLEU score of 23.91 and neural machine translation (NMT) outperforming with a BLEU score of 40.67. Additionally, language-specific morphological analysis, particularly focusing on suffixes, yields further improvements, with SMT achieving a BLEU score of 25.03 and NMT achieving a BLEU score of 44. |
  - An empirical study of low-resource neural machine translation of manipuri in multilingual settings - based neural machine translation system for Manipuri and English, incorporating cross-lingual features, which demonstrates improvement over vanilla multilingual and bilingual baselines, with enhanced performance across Manipuri-English and other Indian language-English translation tasks, including zero-shot translation evaluations. |
  - An Exploratory Study of SMT Versus NMT for the Resource Constraint English to Manipuri Translation - to-Manipuri translation using BLEU, Meteor, TER, and F-measure scores as well as expert evaluation, to determine the most suitable approach for low-resource language pairs. |
  - Low-Resource Indic Languages Translation Using Multilingual Approaches - trained transformers—mBART and mT5—on low-resource Indic languages, including Hindi, Bengali, Assamese, Manipuri, and Mizo, comparing their performance with multiway multilingual translation trained from scratch using a one-to-many and many-to-one approach, highlighting the scalability of multilingual neural machine translation (MNMT) and its potential for improving translation quality in low-resource language settings. |
  - Low-Resource Indic Languages Translation Using Multilingual Approaches - trained transformers—mBART and mT5—on low-resource Indic languages, including Hindi, Bengali, Assamese, Manipuri, and Mizo, comparing their performance with multiway multilingual translation trained from scratch using a one-to-many and many-to-one approach, highlighting the scalability of multilingual neural machine translation (MNMT) and its potential for improving translation quality in low-resource language settings. |
  - Statistical and Neural Machine Translation for Manipuri-English on Intelligence Domain - English machine translation system in an intelligence domain, utilizing 56,678 parallel corpora from open-source intelligence (OSINT) sources, with statistical machine translation (SMT) achieving a BLEU score of 23.91 and neural machine translation (NMT) outperforming with a BLEU score of 40.67. Additionally, language-specific morphological analysis, particularly focusing on suffixes, yields further improvements, with SMT achieving a BLEU score of 25.03 and NMT achieving a BLEU score of 44. |
  - An empirical study of low-resource neural machine translation of manipuri in multilingual settings - based neural machine translation system for Manipuri and English, incorporating cross-lingual features, which demonstrates improvement over vanilla multilingual and bilingual baselines, with enhanced performance across Manipuri-English and other Indian language-English translation tasks, including zero-shot translation evaluations. |
  - An Exploratory Study of SMT Versus NMT for the Resource Constraint English to Manipuri Translation - to-Manipuri translation using BLEU, Meteor, TER, and F-measure scores as well as expert evaluation, to determine the most suitable approach for low-resource language pairs. |
  - Statistical and Neural Machine Translation for Manipuri-English on Intelligence Domain - English machine translation system in an intelligence domain, utilizing 56,678 parallel corpora from open-source intelligence (OSINT) sources, with statistical machine translation (SMT) achieving a BLEU score of 23.91 and neural machine translation (NMT) outperforming with a BLEU score of 40.67. Additionally, language-specific morphological analysis, particularly focusing on suffixes, yields further improvements, with SMT achieving a BLEU score of 25.03 and NMT achieving a BLEU score of 44. |
  - An empirical study of low-resource neural machine translation of manipuri in multilingual settings - based neural machine translation system for Manipuri and English, incorporating cross-lingual features, which demonstrates improvement over vanilla multilingual and bilingual baselines, with enhanced performance across Manipuri-English and other Indian language-English translation tasks, including zero-shot translation evaluations. |
  - An Exploratory Study of SMT Versus NMT for the Resource Constraint English to Manipuri Translation - to-Manipuri translation using BLEU, Meteor, TER, and F-measure scores as well as expert evaluation, to determine the most suitable approach for low-resource language pairs. |
  - Low-Resource Indic Languages Translation Using Multilingual Approaches - trained transformers—mBART and mT5—on low-resource Indic languages, including Hindi, Bengali, Assamese, Manipuri, and Mizo, comparing their performance with multiway multilingual translation trained from scratch using a one-to-many and many-to-one approach, highlighting the scalability of multilingual neural machine translation (MNMT) and its potential for improving translation quality in low-resource language settings. |
  - Statistical and Neural Machine Translation for Manipuri-English on Intelligence Domain - English machine translation system in an intelligence domain, utilizing 56,678 parallel corpora from open-source intelligence (OSINT) sources, with statistical machine translation (SMT) achieving a BLEU score of 23.91 and neural machine translation (NMT) outperforming with a BLEU score of 40.67. Additionally, language-specific morphological analysis, particularly focusing on suffixes, yields further improvements, with SMT achieving a BLEU score of 25.03 and NMT achieving a BLEU score of 44. |
  - An empirical study of low-resource neural machine translation of manipuri in multilingual settings - based neural machine translation system for Manipuri and English, incorporating cross-lingual features, which demonstrates improvement over vanilla multilingual and bilingual baselines, with enhanced performance across Manipuri-English and other Indian language-English translation tasks, including zero-shot translation evaluations. |
  - An Exploratory Study of SMT Versus NMT for the Resource Constraint English to Manipuri Translation - to-Manipuri translation using BLEU, Meteor, TER, and F-measure scores as well as expert evaluation, to determine the most suitable approach for low-resource language pairs. |
  - Low-Resource Indic Languages Translation Using Multilingual Approaches - trained transformers—mBART and mT5—on low-resource Indic languages, including Hindi, Bengali, Assamese, Manipuri, and Mizo, comparing their performance with multiway multilingual translation trained from scratch using a one-to-many and many-to-one approach, highlighting the scalability of multilingual neural machine translation (MNMT) and its potential for improving translation quality in low-resource language settings. |
  - Statistical and Neural Machine Translation for Manipuri-English on Intelligence Domain - English machine translation system in an intelligence domain, utilizing 56,678 parallel corpora from open-source intelligence (OSINT) sources, with statistical machine translation (SMT) achieving a BLEU score of 23.91 and neural machine translation (NMT) outperforming with a BLEU score of 40.67. Additionally, language-specific morphological analysis, particularly focusing on suffixes, yields further improvements, with SMT achieving a BLEU score of 25.03 and NMT achieving a BLEU score of 44. |
  - An empirical study of low-resource neural machine translation of manipuri in multilingual settings - based neural machine translation system for Manipuri and English, incorporating cross-lingual features, which demonstrates improvement over vanilla multilingual and bilingual baselines, with enhanced performance across Manipuri-English and other Indian language-English translation tasks, including zero-shot translation evaluations. |
  - An Exploratory Study of SMT Versus NMT for the Resource Constraint English to Manipuri Translation - to-Manipuri translation using BLEU, Meteor, TER, and F-measure scores as well as expert evaluation, to determine the most suitable approach for low-resource language pairs. |
  - Low-Resource Indic Languages Translation Using Multilingual Approaches - trained transformers—mBART and mT5—on low-resource Indic languages, including Hindi, Bengali, Assamese, Manipuri, and Mizo, comparing their performance with multiway multilingual translation trained from scratch using a one-to-many and many-to-one approach, highlighting the scalability of multilingual neural machine translation (MNMT) and its potential for improving translation quality in low-resource language settings. |
  - Statistical and Neural Machine Translation for Manipuri-English on Intelligence Domain - English machine translation system in an intelligence domain, utilizing 56,678 parallel corpora from open-source intelligence (OSINT) sources, with statistical machine translation (SMT) achieving a BLEU score of 23.91 and neural machine translation (NMT) outperforming with a BLEU score of 40.67. Additionally, language-specific morphological analysis, particularly focusing on suffixes, yields further improvements, with SMT achieving a BLEU score of 25.03 and NMT achieving a BLEU score of 44. |
  - An empirical study of low-resource neural machine translation of manipuri in multilingual settings - based neural machine translation system for Manipuri and English, incorporating cross-lingual features, which demonstrates improvement over vanilla multilingual and bilingual baselines, with enhanced performance across Manipuri-English and other Indian language-English translation tasks, including zero-shot translation evaluations. |
  - An Exploratory Study of SMT Versus NMT for the Resource Constraint English to Manipuri Translation - to-Manipuri translation using BLEU, Meteor, TER, and F-measure scores as well as expert evaluation, to determine the most suitable approach for low-resource language pairs. |
  - Low-Resource Indic Languages Translation Using Multilingual Approaches - trained transformers—mBART and mT5—on low-resource Indic languages, including Hindi, Bengali, Assamese, Manipuri, and Mizo, comparing their performance with multiway multilingual translation trained from scratch using a one-to-many and many-to-one approach, highlighting the scalability of multilingual neural machine translation (MNMT) and its potential for improving translation quality in low-resource language settings. |
  - Statistical and Neural Machine Translation for Manipuri-English on Intelligence Domain - English machine translation system in an intelligence domain, utilizing 56,678 parallel corpora from open-source intelligence (OSINT) sources, with statistical machine translation (SMT) achieving a BLEU score of 23.91 and neural machine translation (NMT) outperforming with a BLEU score of 40.67. Additionally, language-specific morphological analysis, particularly focusing on suffixes, yields further improvements, with SMT achieving a BLEU score of 25.03 and NMT achieving a BLEU score of 44. |
  - An empirical study of low-resource neural machine translation of manipuri in multilingual settings - based neural machine translation system for Manipuri and English, incorporating cross-lingual features, which demonstrates improvement over vanilla multilingual and bilingual baselines, with enhanced performance across Manipuri-English and other Indian language-English translation tasks, including zero-shot translation evaluations. |
  - Low-Resource Indic Languages Translation Using Multilingual Approaches - trained transformers—mBART and mT5—on low-resource Indic languages, including Hindi, Bengali, Assamese, Manipuri, and Mizo, comparing their performance with multiway multilingual translation trained from scratch using a one-to-many and many-to-one approach, highlighting the scalability of multilingual neural machine translation (MNMT) and its potential for improving translation quality in low-resource language settings. |
  - An Exploratory Study of SMT Versus NMT for the Resource Constraint English to Manipuri Translation - to-Manipuri translation using BLEU, Meteor, TER, and F-measure scores as well as expert evaluation, to determine the most suitable approach for low-resource language pairs. |
  - Statistical and Neural Machine Translation for Manipuri-English on Intelligence Domain - English machine translation system in an intelligence domain, utilizing 56,678 parallel corpora from open-source intelligence (OSINT) sources, with statistical machine translation (SMT) achieving a BLEU score of 23.91 and neural machine translation (NMT) outperforming with a BLEU score of 40.67. Additionally, language-specific morphological analysis, particularly focusing on suffixes, yields further improvements, with SMT achieving a BLEU score of 25.03 and NMT achieving a BLEU score of 44. |
  - An empirical study of low-resource neural machine translation of manipuri in multilingual settings - based neural machine translation system for Manipuri and English, incorporating cross-lingual features, which demonstrates improvement over vanilla multilingual and bilingual baselines, with enhanced performance across Manipuri-English and other Indian language-English translation tasks, including zero-shot translation evaluations. |
  - An Exploratory Study of SMT Versus NMT for the Resource Constraint English to Manipuri Translation - to-Manipuri translation using BLEU, Meteor, TER, and F-measure scores as well as expert evaluation, to determine the most suitable approach for low-resource language pairs. |
  - Low-Resource Indic Languages Translation Using Multilingual Approaches - trained transformers—mBART and mT5—on low-resource Indic languages, including Hindi, Bengali, Assamese, Manipuri, and Mizo, comparing their performance with multiway multilingual translation trained from scratch using a one-to-many and many-to-one approach, highlighting the scalability of multilingual neural machine translation (MNMT) and its potential for improving translation quality in low-resource language settings. |
  - Manipuri-English Example Based Machine Translation System - English example-based machine translation system, utilizing parallel corpus alignment techniques including POS tagging, morphological analysis, NER, and chunking, achieving BLEU and NIST scores of 0.137 and 3.361 respectively, outperforming a baseline SMT system with the same training and test data. |
  - Statistical Machine Translation of English-Manipuri using Morpho-syntactic and Semantic Information - Manipuri language pair, highlighting the significance of suffixes, dependency relations, and case markers in translation, resulting in improved translation quality, as evidenced by both BLEU score and subjective evaluation. |
  - Manipuri-English Bidirectional Statistical Machine Translation Systems using Morphology and Dependency Relations - English statistical machine translation systems, highlighting the importance of suffixes, dependency relations, and case markers, with factored BLEU scores improved from 13.045 to 16.873 for English-Manipuri and from 13.452 to 17.573 for Manipuri-English translations, alongside subjective evaluation showing enhanced fluency and adequacy compared to baseline systems. |
  - Integration of Reduplicated Multiword Expressions and Named Entities in a Phrase Based Statistical Machine Translation System - English Phrase Based Statistical Machine Translation (PBSMT) system, utilizing SVM-based machine learning and GIZA++ alignment techniques, resulting in improved BLEU and NIST scores over baseline systems, as well as subjective evaluation indicating enhanced adequacy |
  - Addressing some Issues of Data Sparsity towards Improving English-Manipuri SMT using Morphological Information
  - Taste of Two Different Flavours: Which Manipuri Script Works Better for English-Manipuri Language Pair SMT Systems? - based statistical machine translation (PBSMT) systems for the English-Manipuri language pair using Bengali script and transliterated Meitei Mayek script, showing that the Bengali script-based PBSMT outperforms in terms of BLEU and NIST scores, despite slight variations in subjective evaluation against automatic scores. |
  - A Review on Electronic Dictionary and Machine Translation System Developed in North-East India - dictionary) and Machine Translation (MT) systems, highlighting their significance in Natural Language Processing (NLP), particularly in multilingual regions like North-East (NE) India, where few such systems have been developed, underscoring the growing demand for research in this area. |
  - English to Manipuri and Mizo Post-Editing Effort and its Impact on Low Resource Machine Translation - editing effort in building a parallel dataset for English-Manipuri and English-Mizo, revealing positive correlations between technical effort and function words for both language pairs, and negative correlations between technical effort and noun words for English-Mizo, with an increase in HBLEU of up to 4.6 for English-Manipuri when using the post-edited dataset for incremental training. |
  - Zero-shot translation among Indian languages - shot translation on low-resource Indian languages, achieving an increase in translation accuracy, with a balanced data settings score multiplied by 7 for Manipuri to Hindi during Round-III of zero-shot translation. |
  - Manipuri-English Machine Translation using Comparable Corpus - English comparable corpus, demonstrating feasibility and identifying future directions for developing effective MT for the Manipuri-English language pair under unsupervised scenarios. |
  - Statistical and Neural Machine Translation for Manipuri-English on Intelligence Domain - English machine translation system in an intelligence domain, utilizing 56,678 parallel corpora from open-source intelligence (OSINT) sources, with statistical machine translation (SMT) achieving a BLEU score of 23.91 and neural machine translation (NMT) outperforming with a BLEU score of 40.67. Additionally, language-specific morphological analysis, particularly focusing on suffixes, yields further improvements, with SMT achieving a BLEU score of 25.03 and NMT achieving a BLEU score of 44. |
  - An empirical study of low-resource neural machine translation of manipuri in multilingual settings - based neural machine translation system for Manipuri and English, incorporating cross-lingual features, which demonstrates improvement over vanilla multilingual and bilingual baselines, with enhanced performance across Manipuri-English and other Indian language-English translation tasks, including zero-shot translation evaluations. |
  - Introducing EM-FT for Manipuri-English Neural Machine Translation - FT consistently outperforms alternatives, while noting a negative impact on translation accuracy with additional training data from a different domain. |
  - An Analysis of Phrase based SMT for English to Manipuri Language - based Statistical Machine Translation (SMT) system from English to Manipuri, leveraging the Moses toolkit and Bengali script, and evaluates its performance using the BLEU metric on tourism, agriculture, and entertainment corpora. |
  - An Exploratory Study of SMT Versus NMT for the Resource Constraint English to Manipuri Translation - to-Manipuri translation using BLEU, Meteor, TER, and F-measure scores as well as expert evaluation, to determine the most suitable approach for low-resource language pairs. |
  - Subwords to Word Back Composition for Morphologically Rich Languages in Neural Machine Translation - English, Tamil-English, and Marathi-English translation tasks, highlighting the importance of leveraging word boundary information and interrelationships between word morphemes in NMT. |
  - Low-Resource Indic Languages Translation Using Multilingual Approaches - trained transformers—mBART and mT5—on low-resource Indic languages, including Hindi, Bengali, Assamese, Manipuri, and Mizo, comparing their performance with multiway multilingual translation trained from scratch using a one-to-many and many-to-one approach, highlighting the scalability of multilingual neural machine translation (MNMT) and its potential for improving translation quality in low-resource language settings. |
  - Findings of the WMT 2023 Shared Task on Low-Resource Indic Language - resource Indic language translation task conducted alongside the Eighth Conference on Machine Translation (WMT) 2023, where participants were tasked with developing machine translation systems for English-Assamese, English-Mizo, English-Khasi, and English-Manipuri language pairs. The evaluation of these systems will include both automatic metrics (BLEU, TER, RIBES, COMET, ChrF) and human assessment, utilizing the IndicNE-Corp1.0 dataset, comprising parallel and monolingual corpora for northeastern Indic languages like Assamese, Mizo, Khasi, and Manipuri. |
  - NITS-CNLP Low-Resource Neural Machine Translation Systems of English-Manipuri Language Pair - based Neural Machine Translation (NMT) system developed by NITS-CNLP for the English-Manipuri language pair, achieving BLEU scores of 22.75 for English to Manipuri and 26.92 for Manipuri to English translations, along with character level n-gram F-score (chrF), RIBES, TER, and COMET evaluations. |
  - Neural Machine Translation for English - Manipuri and English - Assamese - NITS, utilized the NMT transformer model for English to/from Assamese and English to/from Manipuri language translation, achieving BLEU scores of 15.02 and 18.7 for English to Manipuri and Manipuri to English translations respectively, as well as 5.47 for English to Assamese and 8.5 for Assamese to English translations.|
  - Statistical and Neural Machine Translation for Manipuri-English on Intelligence Domain - English machine translation system in an intelligence domain, utilizing 56,678 parallel corpora from open-source intelligence (OSINT) sources, with statistical machine translation (SMT) achieving a BLEU score of 23.91 and neural machine translation (NMT) outperforming with a BLEU score of 40.67. Additionally, language-specific morphological analysis, particularly focusing on suffixes, yields further improvements, with SMT achieving a BLEU score of 25.03 and NMT achieving a BLEU score of 44. |
  - Statistical and Neural Machine Translation for Manipuri-English on Intelligence Domain - English machine translation system in an intelligence domain, utilizing 56,678 parallel corpora from open-source intelligence (OSINT) sources, with statistical machine translation (SMT) achieving a BLEU score of 23.91 and neural machine translation (NMT) outperforming with a BLEU score of 40.67. Additionally, language-specific morphological analysis, particularly focusing on suffixes, yields further improvements, with SMT achieving a BLEU score of 25.03 and NMT achieving a BLEU score of 44. |
  - An empirical study of low-resource neural machine translation of manipuri in multilingual settings - based neural machine translation system for Manipuri and English, incorporating cross-lingual features, which demonstrates improvement over vanilla multilingual and bilingual baselines, with enhanced performance across Manipuri-English and other Indian language-English translation tasks, including zero-shot translation evaluations. |
  - An Exploratory Study of SMT Versus NMT for the Resource Constraint English to Manipuri Translation - to-Manipuri translation using BLEU, Meteor, TER, and F-measure scores as well as expert evaluation, to determine the most suitable approach for low-resource language pairs. |
  - Low-Resource Indic Languages Translation Using Multilingual Approaches - trained transformers—mBART and mT5—on low-resource Indic languages, including Hindi, Bengali, Assamese, Manipuri, and Mizo, comparing their performance with multiway multilingual translation trained from scratch using a one-to-many and many-to-one approach, highlighting the scalability of multilingual neural machine translation (MNMT) and its potential for improving translation quality in low-resource language settings. |
  - Statistical and Neural Machine Translation for Manipuri-English on Intelligence Domain - English machine translation system in an intelligence domain, utilizing 56,678 parallel corpora from open-source intelligence (OSINT) sources, with statistical machine translation (SMT) achieving a BLEU score of 23.91 and neural machine translation (NMT) outperforming with a BLEU score of 40.67. Additionally, language-specific morphological analysis, particularly focusing on suffixes, yields further improvements, with SMT achieving a BLEU score of 25.03 and NMT achieving a BLEU score of 44. |
  - An empirical study of low-resource neural machine translation of manipuri in multilingual settings - based neural machine translation system for Manipuri and English, incorporating cross-lingual features, which demonstrates improvement over vanilla multilingual and bilingual baselines, with enhanced performance across Manipuri-English and other Indian language-English translation tasks, including zero-shot translation evaluations. |
  - An Exploratory Study of SMT Versus NMT for the Resource Constraint English to Manipuri Translation - to-Manipuri translation using BLEU, Meteor, TER, and F-measure scores as well as expert evaluation, to determine the most suitable approach for low-resource language pairs. |
  - Low-Resource Indic Languages Translation Using Multilingual Approaches - trained transformers—mBART and mT5—on low-resource Indic languages, including Hindi, Bengali, Assamese, Manipuri, and Mizo, comparing their performance with multiway multilingual translation trained from scratch using a one-to-many and many-to-one approach, highlighting the scalability of multilingual neural machine translation (MNMT) and its potential for improving translation quality in low-resource language settings. |
  - Statistical and Neural Machine Translation for Manipuri-English on Intelligence Domain - English machine translation system in an intelligence domain, utilizing 56,678 parallel corpora from open-source intelligence (OSINT) sources, with statistical machine translation (SMT) achieving a BLEU score of 23.91 and neural machine translation (NMT) outperforming with a BLEU score of 40.67. Additionally, language-specific morphological analysis, particularly focusing on suffixes, yields further improvements, with SMT achieving a BLEU score of 25.03 and NMT achieving a BLEU score of 44. |
  - An empirical study of low-resource neural machine translation of manipuri in multilingual settings - based neural machine translation system for Manipuri and English, incorporating cross-lingual features, which demonstrates improvement over vanilla multilingual and bilingual baselines, with enhanced performance across Manipuri-English and other Indian language-English translation tasks, including zero-shot translation evaluations. |
  - An Exploratory Study of SMT Versus NMT for the Resource Constraint English to Manipuri Translation - to-Manipuri translation using BLEU, Meteor, TER, and F-measure scores as well as expert evaluation, to determine the most suitable approach for low-resource language pairs. |
  - Low-Resource Indic Languages Translation Using Multilingual Approaches - trained transformers—mBART and mT5—on low-resource Indic languages, including Hindi, Bengali, Assamese, Manipuri, and Mizo, comparing their performance with multiway multilingual translation trained from scratch using a one-to-many and many-to-one approach, highlighting the scalability of multilingual neural machine translation (MNMT) and its potential for improving translation quality in low-resource language settings. |
  - Statistical and Neural Machine Translation for Manipuri-English on Intelligence Domain - English machine translation system in an intelligence domain, utilizing 56,678 parallel corpora from open-source intelligence (OSINT) sources, with statistical machine translation (SMT) achieving a BLEU score of 23.91 and neural machine translation (NMT) outperforming with a BLEU score of 40.67. Additionally, language-specific morphological analysis, particularly focusing on suffixes, yields further improvements, with SMT achieving a BLEU score of 25.03 and NMT achieving a BLEU score of 44. |
  - An empirical study of low-resource neural machine translation of manipuri in multilingual settings - based neural machine translation system for Manipuri and English, incorporating cross-lingual features, which demonstrates improvement over vanilla multilingual and bilingual baselines, with enhanced performance across Manipuri-English and other Indian language-English translation tasks, including zero-shot translation evaluations. |
  - An Exploratory Study of SMT Versus NMT for the Resource Constraint English to Manipuri Translation - to-Manipuri translation using BLEU, Meteor, TER, and F-measure scores as well as expert evaluation, to determine the most suitable approach for low-resource language pairs. |
  - Low-Resource Indic Languages Translation Using Multilingual Approaches - trained transformers—mBART and mT5—on low-resource Indic languages, including Hindi, Bengali, Assamese, Manipuri, and Mizo, comparing their performance with multiway multilingual translation trained from scratch using a one-to-many and many-to-one approach, highlighting the scalability of multilingual neural machine translation (MNMT) and its potential for improving translation quality in low-resource language settings. |
  - Low-Resource Indic Languages Translation Using Multilingual Approaches - trained transformers—mBART and mT5—on low-resource Indic languages, including Hindi, Bengali, Assamese, Manipuri, and Mizo, comparing their performance with multiway multilingual translation trained from scratch using a one-to-many and many-to-one approach, highlighting the scalability of multilingual neural machine translation (MNMT) and its potential for improving translation quality in low-resource language settings. |
  - Statistical and Neural Machine Translation for Manipuri-English on Intelligence Domain - English machine translation system in an intelligence domain, utilizing 56,678 parallel corpora from open-source intelligence (OSINT) sources, with statistical machine translation (SMT) achieving a BLEU score of 23.91 and neural machine translation (NMT) outperforming with a BLEU score of 40.67. Additionally, language-specific morphological analysis, particularly focusing on suffixes, yields further improvements, with SMT achieving a BLEU score of 25.03 and NMT achieving a BLEU score of 44. |
  - An empirical study of low-resource neural machine translation of manipuri in multilingual settings - based neural machine translation system for Manipuri and English, incorporating cross-lingual features, which demonstrates improvement over vanilla multilingual and bilingual baselines, with enhanced performance across Manipuri-English and other Indian language-English translation tasks, including zero-shot translation evaluations. |
  - An Exploratory Study of SMT Versus NMT for the Resource Constraint English to Manipuri Translation - to-Manipuri translation using BLEU, Meteor, TER, and F-measure scores as well as expert evaluation, to determine the most suitable approach for low-resource language pairs. |
  - Statistical and Neural Machine Translation for Manipuri-English on Intelligence Domain - English machine translation system in an intelligence domain, utilizing 56,678 parallel corpora from open-source intelligence (OSINT) sources, with statistical machine translation (SMT) achieving a BLEU score of 23.91 and neural machine translation (NMT) outperforming with a BLEU score of 40.67. Additionally, language-specific morphological analysis, particularly focusing on suffixes, yields further improvements, with SMT achieving a BLEU score of 25.03 and NMT achieving a BLEU score of 44. |
  - An empirical study of low-resource neural machine translation of manipuri in multilingual settings - based neural machine translation system for Manipuri and English, incorporating cross-lingual features, which demonstrates improvement over vanilla multilingual and bilingual baselines, with enhanced performance across Manipuri-English and other Indian language-English translation tasks, including zero-shot translation evaluations. |
  - An Exploratory Study of SMT Versus NMT for the Resource Constraint English to Manipuri Translation - to-Manipuri translation using BLEU, Meteor, TER, and F-measure scores as well as expert evaluation, to determine the most suitable approach for low-resource language pairs. |
  - Low-Resource Indic Languages Translation Using Multilingual Approaches - trained transformers—mBART and mT5—on low-resource Indic languages, including Hindi, Bengali, Assamese, Manipuri, and Mizo, comparing their performance with multiway multilingual translation trained from scratch using a one-to-many and many-to-one approach, highlighting the scalability of multilingual neural machine translation (MNMT) and its potential for improving translation quality in low-resource language settings. |
  - Low-Resource Indic Languages Translation Using Multilingual Approaches - trained transformers—mBART and mT5—on low-resource Indic languages, including Hindi, Bengali, Assamese, Manipuri, and Mizo, comparing their performance with multiway multilingual translation trained from scratch using a one-to-many and many-to-one approach, highlighting the scalability of multilingual neural machine translation (MNMT) and its potential for improving translation quality in low-resource language settings. |
  - Statistical and Neural Machine Translation for Manipuri-English on Intelligence Domain - English machine translation system in an intelligence domain, utilizing 56,678 parallel corpora from open-source intelligence (OSINT) sources, with statistical machine translation (SMT) achieving a BLEU score of 23.91 and neural machine translation (NMT) outperforming with a BLEU score of 40.67. Additionally, language-specific morphological analysis, particularly focusing on suffixes, yields further improvements, with SMT achieving a BLEU score of 25.03 and NMT achieving a BLEU score of 44. |
  - An empirical study of low-resource neural machine translation of manipuri in multilingual settings - based neural machine translation system for Manipuri and English, incorporating cross-lingual features, which demonstrates improvement over vanilla multilingual and bilingual baselines, with enhanced performance across Manipuri-English and other Indian language-English translation tasks, including zero-shot translation evaluations. |
  - An Exploratory Study of SMT Versus NMT for the Resource Constraint English to Manipuri Translation - to-Manipuri translation using BLEU, Meteor, TER, and F-measure scores as well as expert evaluation, to determine the most suitable approach for low-resource language pairs. |
  - Statistical and Neural Machine Translation for Manipuri-English on Intelligence Domain - English machine translation system in an intelligence domain, utilizing 56,678 parallel corpora from open-source intelligence (OSINT) sources, with statistical machine translation (SMT) achieving a BLEU score of 23.91 and neural machine translation (NMT) outperforming with a BLEU score of 40.67. Additionally, language-specific morphological analysis, particularly focusing on suffixes, yields further improvements, with SMT achieving a BLEU score of 25.03 and NMT achieving a BLEU score of 44. |
  - An empirical study of low-resource neural machine translation of manipuri in multilingual settings - based neural machine translation system for Manipuri and English, incorporating cross-lingual features, which demonstrates improvement over vanilla multilingual and bilingual baselines, with enhanced performance across Manipuri-English and other Indian language-English translation tasks, including zero-shot translation evaluations. |
  - Low-Resource Indic Languages Translation Using Multilingual Approaches - trained transformers—mBART and mT5—on low-resource Indic languages, including Hindi, Bengali, Assamese, Manipuri, and Mizo, comparing their performance with multiway multilingual translation trained from scratch using a one-to-many and many-to-one approach, highlighting the scalability of multilingual neural machine translation (MNMT) and its potential for improving translation quality in low-resource language settings. |
  - Statistical and Neural Machine Translation for Manipuri-English on Intelligence Domain - English machine translation system in an intelligence domain, utilizing 56,678 parallel corpora from open-source intelligence (OSINT) sources, with statistical machine translation (SMT) achieving a BLEU score of 23.91 and neural machine translation (NMT) outperforming with a BLEU score of 40.67. Additionally, language-specific morphological analysis, particularly focusing on suffixes, yields further improvements, with SMT achieving a BLEU score of 25.03 and NMT achieving a BLEU score of 44. |
  - Low-Resource Indic Languages Translation Using Multilingual Approaches - trained transformers—mBART and mT5—on low-resource Indic languages, including Hindi, Bengali, Assamese, Manipuri, and Mizo, comparing their performance with multiway multilingual translation trained from scratch using a one-to-many and many-to-one approach, highlighting the scalability of multilingual neural machine translation (MNMT) and its potential for improving translation quality in low-resource language settings. |
  - An empirical study of low-resource neural machine translation of manipuri in multilingual settings - based neural machine translation system for Manipuri and English, incorporating cross-lingual features, which demonstrates improvement over vanilla multilingual and bilingual baselines, with enhanced performance across Manipuri-English and other Indian language-English translation tasks, including zero-shot translation evaluations. |
  - An Exploratory Study of SMT Versus NMT for the Resource Constraint English to Manipuri Translation - to-Manipuri translation using BLEU, Meteor, TER, and F-measure scores as well as expert evaluation, to determine the most suitable approach for low-resource language pairs. |
  - Statistical and Neural Machine Translation for Manipuri-English on Intelligence Domain - English machine translation system in an intelligence domain, utilizing 56,678 parallel corpora from open-source intelligence (OSINT) sources, with statistical machine translation (SMT) achieving a BLEU score of 23.91 and neural machine translation (NMT) outperforming with a BLEU score of 40.67. Additionally, language-specific morphological analysis, particularly focusing on suffixes, yields further improvements, with SMT achieving a BLEU score of 25.03 and NMT achieving a BLEU score of 44. |
  - An empirical study of low-resource neural machine translation of manipuri in multilingual settings - based neural machine translation system for Manipuri and English, incorporating cross-lingual features, which demonstrates improvement over vanilla multilingual and bilingual baselines, with enhanced performance across Manipuri-English and other Indian language-English translation tasks, including zero-shot translation evaluations. |
  - An Exploratory Study of SMT Versus NMT for the Resource Constraint English to Manipuri Translation - to-Manipuri translation using BLEU, Meteor, TER, and F-measure scores as well as expert evaluation, to determine the most suitable approach for low-resource language pairs. |
  - Low-Resource Indic Languages Translation Using Multilingual Approaches - trained transformers—mBART and mT5—on low-resource Indic languages, including Hindi, Bengali, Assamese, Manipuri, and Mizo, comparing their performance with multiway multilingual translation trained from scratch using a one-to-many and many-to-one approach, highlighting the scalability of multilingual neural machine translation (MNMT) and its potential for improving translation quality in low-resource language settings. |
  - Statistical and Neural Machine Translation for Manipuri-English on Intelligence Domain - English machine translation system in an intelligence domain, utilizing 56,678 parallel corpora from open-source intelligence (OSINT) sources, with statistical machine translation (SMT) achieving a BLEU score of 23.91 and neural machine translation (NMT) outperforming with a BLEU score of 40.67. Additionally, language-specific morphological analysis, particularly focusing on suffixes, yields further improvements, with SMT achieving a BLEU score of 25.03 and NMT achieving a BLEU score of 44. |
  - An empirical study of low-resource neural machine translation of manipuri in multilingual settings - based neural machine translation system for Manipuri and English, incorporating cross-lingual features, which demonstrates improvement over vanilla multilingual and bilingual baselines, with enhanced performance across Manipuri-English and other Indian language-English translation tasks, including zero-shot translation evaluations. |
  - An Exploratory Study of SMT Versus NMT for the Resource Constraint English to Manipuri Translation - to-Manipuri translation using BLEU, Meteor, TER, and F-measure scores as well as expert evaluation, to determine the most suitable approach for low-resource language pairs. |
  - Low-Resource Indic Languages Translation Using Multilingual Approaches - trained transformers—mBART and mT5—on low-resource Indic languages, including Hindi, Bengali, Assamese, Manipuri, and Mizo, comparing their performance with multiway multilingual translation trained from scratch using a one-to-many and many-to-one approach, highlighting the scalability of multilingual neural machine translation (MNMT) and its potential for improving translation quality in low-resource language settings. |
  - Statistical and Neural Machine Translation for Manipuri-English on Intelligence Domain - English machine translation system in an intelligence domain, utilizing 56,678 parallel corpora from open-source intelligence (OSINT) sources, with statistical machine translation (SMT) achieving a BLEU score of 23.91 and neural machine translation (NMT) outperforming with a BLEU score of 40.67. Additionally, language-specific morphological analysis, particularly focusing on suffixes, yields further improvements, with SMT achieving a BLEU score of 25.03 and NMT achieving a BLEU score of 44. |
  - An empirical study of low-resource neural machine translation of manipuri in multilingual settings - based neural machine translation system for Manipuri and English, incorporating cross-lingual features, which demonstrates improvement over vanilla multilingual and bilingual baselines, with enhanced performance across Manipuri-English and other Indian language-English translation tasks, including zero-shot translation evaluations. |
  - Low-Resource Indic Languages Translation Using Multilingual Approaches - trained transformers—mBART and mT5—on low-resource Indic languages, including Hindi, Bengali, Assamese, Manipuri, and Mizo, comparing their performance with multiway multilingual translation trained from scratch using a one-to-many and many-to-one approach, highlighting the scalability of multilingual neural machine translation (MNMT) and its potential for improving translation quality in low-resource language settings. |
  - Statistical and Neural Machine Translation for Manipuri-English on Intelligence Domain - English machine translation system in an intelligence domain, utilizing 56,678 parallel corpora from open-source intelligence (OSINT) sources, with statistical machine translation (SMT) achieving a BLEU score of 23.91 and neural machine translation (NMT) outperforming with a BLEU score of 40.67. Additionally, language-specific morphological analysis, particularly focusing on suffixes, yields further improvements, with SMT achieving a BLEU score of 25.03 and NMT achieving a BLEU score of 44. |
  - An empirical study of low-resource neural machine translation of manipuri in multilingual settings - based neural machine translation system for Manipuri and English, incorporating cross-lingual features, which demonstrates improvement over vanilla multilingual and bilingual baselines, with enhanced performance across Manipuri-English and other Indian language-English translation tasks, including zero-shot translation evaluations. |
  - Low-Resource Indic Languages Translation Using Multilingual Approaches - trained transformers—mBART and mT5—on low-resource Indic languages, including Hindi, Bengali, Assamese, Manipuri, and Mizo, comparing their performance with multiway multilingual translation trained from scratch using a one-to-many and many-to-one approach, highlighting the scalability of multilingual neural machine translation (MNMT) and its potential for improving translation quality in low-resource language settings. |
  - Statistical and Neural Machine Translation for Manipuri-English on Intelligence Domain - English machine translation system in an intelligence domain, utilizing 56,678 parallel corpora from open-source intelligence (OSINT) sources, with statistical machine translation (SMT) achieving a BLEU score of 23.91 and neural machine translation (NMT) outperforming with a BLEU score of 40.67. Additionally, language-specific morphological analysis, particularly focusing on suffixes, yields further improvements, with SMT achieving a BLEU score of 25.03 and NMT achieving a BLEU score of 44. |
  - An empirical study of low-resource neural machine translation of manipuri in multilingual settings - based neural machine translation system for Manipuri and English, incorporating cross-lingual features, which demonstrates improvement over vanilla multilingual and bilingual baselines, with enhanced performance across Manipuri-English and other Indian language-English translation tasks, including zero-shot translation evaluations. |
  - An Exploratory Study of SMT Versus NMT for the Resource Constraint English to Manipuri Translation - to-Manipuri translation using BLEU, Meteor, TER, and F-measure scores as well as expert evaluation, to determine the most suitable approach for low-resource language pairs. |
  - Low-Resource Indic Languages Translation Using Multilingual Approaches - trained transformers—mBART and mT5—on low-resource Indic languages, including Hindi, Bengali, Assamese, Manipuri, and Mizo, comparing their performance with multiway multilingual translation trained from scratch using a one-to-many and many-to-one approach, highlighting the scalability of multilingual neural machine translation (MNMT) and its potential for improving translation quality in low-resource language settings. |
  - An empirical study of low-resource neural machine translation of manipuri in multilingual settings - based neural machine translation system for Manipuri and English, incorporating cross-lingual features, which demonstrates improvement over vanilla multilingual and bilingual baselines, with enhanced performance across Manipuri-English and other Indian language-English translation tasks, including zero-shot translation evaluations. |
  - Low-Resource Indic Languages Translation Using Multilingual Approaches - trained transformers—mBART and mT5—on low-resource Indic languages, including Hindi, Bengali, Assamese, Manipuri, and Mizo, comparing their performance with multiway multilingual translation trained from scratch using a one-to-many and many-to-one approach, highlighting the scalability of multilingual neural machine translation (MNMT) and its potential for improving translation quality in low-resource language settings. |
  - Statistical and Neural Machine Translation for Manipuri-English on Intelligence Domain - English machine translation system in an intelligence domain, utilizing 56,678 parallel corpora from open-source intelligence (OSINT) sources, with statistical machine translation (SMT) achieving a BLEU score of 23.91 and neural machine translation (NMT) outperforming with a BLEU score of 40.67. Additionally, language-specific morphological analysis, particularly focusing on suffixes, yields further improvements, with SMT achieving a BLEU score of 25.03 and NMT achieving a BLEU score of 44. |
  - Low resource machine translation of english–manipuri: A semi-supervised approach - supervised neural machine translation system for English-Manipuri, employing self-training and back-translation techniques, yielding a +0.9 BLEU score improvement with external noise introduction, and outperforming supervised and mBART baselines by up to +4.5 and +1.2 BLEU improvements respectively. |
  - An Exploratory Study of SMT Versus NMT for the Resource Constraint English to Manipuri Translation - to-Manipuri translation using BLEU, Meteor, TER, and F-measure scores as well as expert evaluation, to determine the most suitable approach for low-resource language pairs. |
  - Low-Resource Indic Languages Translation Using Multilingual Approaches - trained transformers—mBART and mT5—on low-resource Indic languages, including Hindi, Bengali, Assamese, Manipuri, and Mizo, comparing their performance with multiway multilingual translation trained from scratch using a one-to-many and many-to-one approach, highlighting the scalability of multilingual neural machine translation (MNMT) and its potential for improving translation quality in low-resource language settings. |
  - Statistical and Neural Machine Translation for Manipuri-English on Intelligence Domain - English machine translation system in an intelligence domain, utilizing 56,678 parallel corpora from open-source intelligence (OSINT) sources, with statistical machine translation (SMT) achieving a BLEU score of 23.91 and neural machine translation (NMT) outperforming with a BLEU score of 40.67. Additionally, language-specific morphological analysis, particularly focusing on suffixes, yields further improvements, with SMT achieving a BLEU score of 25.03 and NMT achieving a BLEU score of 44. |
  - An empirical study of low-resource neural machine translation of manipuri in multilingual settings - based neural machine translation system for Manipuri and English, incorporating cross-lingual features, which demonstrates improvement over vanilla multilingual and bilingual baselines, with enhanced performance across Manipuri-English and other Indian language-English translation tasks, including zero-shot translation evaluations. |
  - An empirical study of low-resource neural machine translation of manipuri in multilingual settings - based neural machine translation system for Manipuri and English, incorporating cross-lingual features, which demonstrates improvement over vanilla multilingual and bilingual baselines, with enhanced performance across Manipuri-English and other Indian language-English translation tasks, including zero-shot translation evaluations. |
  - Low-Resource Indic Languages Translation Using Multilingual Approaches - trained transformers—mBART and mT5—on low-resource Indic languages, including Hindi, Bengali, Assamese, Manipuri, and Mizo, comparing their performance with multiway multilingual translation trained from scratch using a one-to-many and many-to-one approach, highlighting the scalability of multilingual neural machine translation (MNMT) and its potential for improving translation quality in low-resource language settings. |
  - Statistical and Neural Machine Translation for Manipuri-English on Intelligence Domain - English machine translation system in an intelligence domain, utilizing 56,678 parallel corpora from open-source intelligence (OSINT) sources, with statistical machine translation (SMT) achieving a BLEU score of 23.91 and neural machine translation (NMT) outperforming with a BLEU score of 40.67. Additionally, language-specific morphological analysis, particularly focusing on suffixes, yields further improvements, with SMT achieving a BLEU score of 25.03 and NMT achieving a BLEU score of 44. |
  - An empirical study of low-resource neural machine translation of manipuri in multilingual settings - based neural machine translation system for Manipuri and English, incorporating cross-lingual features, which demonstrates improvement over vanilla multilingual and bilingual baselines, with enhanced performance across Manipuri-English and other Indian language-English translation tasks, including zero-shot translation evaluations. |
  - An Exploratory Study of SMT Versus NMT for the Resource Constraint English to Manipuri Translation - to-Manipuri translation using BLEU, Meteor, TER, and F-measure scores as well as expert evaluation, to determine the most suitable approach for low-resource language pairs. |
  - Low-Resource Indic Languages Translation Using Multilingual Approaches - trained transformers—mBART and mT5—on low-resource Indic languages, including Hindi, Bengali, Assamese, Manipuri, and Mizo, comparing their performance with multiway multilingual translation trained from scratch using a one-to-many and many-to-one approach, highlighting the scalability of multilingual neural machine translation (MNMT) and its potential for improving translation quality in low-resource language settings. |
  - Statistical and Neural Machine Translation for Manipuri-English on Intelligence Domain - English machine translation system in an intelligence domain, utilizing 56,678 parallel corpora from open-source intelligence (OSINT) sources, with statistical machine translation (SMT) achieving a BLEU score of 23.91 and neural machine translation (NMT) outperforming with a BLEU score of 40.67. Additionally, language-specific morphological analysis, particularly focusing on suffixes, yields further improvements, with SMT achieving a BLEU score of 25.03 and NMT achieving a BLEU score of 44. |
  - An empirical study of low-resource neural machine translation of manipuri in multilingual settings - based neural machine translation system for Manipuri and English, incorporating cross-lingual features, which demonstrates improvement over vanilla multilingual and bilingual baselines, with enhanced performance across Manipuri-English and other Indian language-English translation tasks, including zero-shot translation evaluations. |
  - An Exploratory Study of SMT Versus NMT for the Resource Constraint English to Manipuri Translation - to-Manipuri translation using BLEU, Meteor, TER, and F-measure scores as well as expert evaluation, to determine the most suitable approach for low-resource language pairs. |
  - Low-Resource Indic Languages Translation Using Multilingual Approaches - trained transformers—mBART and mT5—on low-resource Indic languages, including Hindi, Bengali, Assamese, Manipuri, and Mizo, comparing their performance with multiway multilingual translation trained from scratch using a one-to-many and many-to-one approach, highlighting the scalability of multilingual neural machine translation (MNMT) and its potential for improving translation quality in low-resource language settings. |
  - Statistical and Neural Machine Translation for Manipuri-English on Intelligence Domain - English machine translation system in an intelligence domain, utilizing 56,678 parallel corpora from open-source intelligence (OSINT) sources, with statistical machine translation (SMT) achieving a BLEU score of 23.91 and neural machine translation (NMT) outperforming with a BLEU score of 40.67. Additionally, language-specific morphological analysis, particularly focusing on suffixes, yields further improvements, with SMT achieving a BLEU score of 25.03 and NMT achieving a BLEU score of 44. |
  - An empirical study of low-resource neural machine translation of manipuri in multilingual settings - based neural machine translation system for Manipuri and English, incorporating cross-lingual features, which demonstrates improvement over vanilla multilingual and bilingual baselines, with enhanced performance across Manipuri-English and other Indian language-English translation tasks, including zero-shot translation evaluations. |
  - An Exploratory Study of SMT Versus NMT for the Resource Constraint English to Manipuri Translation - to-Manipuri translation using BLEU, Meteor, TER, and F-measure scores as well as expert evaluation, to determine the most suitable approach for low-resource language pairs. |
  - Low-Resource Indic Languages Translation Using Multilingual Approaches - trained transformers—mBART and mT5—on low-resource Indic languages, including Hindi, Bengali, Assamese, Manipuri, and Mizo, comparing their performance with multiway multilingual translation trained from scratch using a one-to-many and many-to-one approach, highlighting the scalability of multilingual neural machine translation (MNMT) and its potential for improving translation quality in low-resource language settings. |
  - An empirical study of low-resource neural machine translation of manipuri in multilingual settings - based neural machine translation system for Manipuri and English, incorporating cross-lingual features, which demonstrates improvement over vanilla multilingual and bilingual baselines, with enhanced performance across Manipuri-English and other Indian language-English translation tasks, including zero-shot translation evaluations. |
  - Low-Resource Indic Languages Translation Using Multilingual Approaches - trained transformers—mBART and mT5—on low-resource Indic languages, including Hindi, Bengali, Assamese, Manipuri, and Mizo, comparing their performance with multiway multilingual translation trained from scratch using a one-to-many and many-to-one approach, highlighting the scalability of multilingual neural machine translation (MNMT) and its potential for improving translation quality in low-resource language settings. |
  - Statistical and Neural Machine Translation for Manipuri-English on Intelligence Domain - English machine translation system in an intelligence domain, utilizing 56,678 parallel corpora from open-source intelligence (OSINT) sources, with statistical machine translation (SMT) achieving a BLEU score of 23.91 and neural machine translation (NMT) outperforming with a BLEU score of 40.67. Additionally, language-specific morphological analysis, particularly focusing on suffixes, yields further improvements, with SMT achieving a BLEU score of 25.03 and NMT achieving a BLEU score of 44. |
  - An empirical study of low-resource neural machine translation of manipuri in multilingual settings - based neural machine translation system for Manipuri and English, incorporating cross-lingual features, which demonstrates improvement over vanilla multilingual and bilingual baselines, with enhanced performance across Manipuri-English and other Indian language-English translation tasks, including zero-shot translation evaluations. |
  - Low-Resource Indic Languages Translation Using Multilingual Approaches - trained transformers—mBART and mT5—on low-resource Indic languages, including Hindi, Bengali, Assamese, Manipuri, and Mizo, comparing their performance with multiway multilingual translation trained from scratch using a one-to-many and many-to-one approach, highlighting the scalability of multilingual neural machine translation (MNMT) and its potential for improving translation quality in low-resource language settings. |
  - Statistical and Neural Machine Translation for Manipuri-English on Intelligence Domain - English machine translation system in an intelligence domain, utilizing 56,678 parallel corpora from open-source intelligence (OSINT) sources, with statistical machine translation (SMT) achieving a BLEU score of 23.91 and neural machine translation (NMT) outperforming with a BLEU score of 40.67. Additionally, language-specific morphological analysis, particularly focusing on suffixes, yields further improvements, with SMT achieving a BLEU score of 25.03 and NMT achieving a BLEU score of 44. |
  - An empirical study of low-resource neural machine translation of manipuri in multilingual settings - based neural machine translation system for Manipuri and English, incorporating cross-lingual features, which demonstrates improvement over vanilla multilingual and bilingual baselines, with enhanced performance across Manipuri-English and other Indian language-English translation tasks, including zero-shot translation evaluations. |
  - Low-Resource Indic Languages Translation Using Multilingual Approaches - trained transformers—mBART and mT5—on low-resource Indic languages, including Hindi, Bengali, Assamese, Manipuri, and Mizo, comparing their performance with multiway multilingual translation trained from scratch using a one-to-many and many-to-one approach, highlighting the scalability of multilingual neural machine translation (MNMT) and its potential for improving translation quality in low-resource language settings. |
  - Statistical and Neural Machine Translation for Manipuri-English on Intelligence Domain - English machine translation system in an intelligence domain, utilizing 56,678 parallel corpora from open-source intelligence (OSINT) sources, with statistical machine translation (SMT) achieving a BLEU score of 23.91 and neural machine translation (NMT) outperforming with a BLEU score of 40.67. Additionally, language-specific morphological analysis, particularly focusing on suffixes, yields further improvements, with SMT achieving a BLEU score of 25.03 and NMT achieving a BLEU score of 44. |
- Transliteration
  - Manipuri Transliteration from Bengali Script to Meitei Mayek: A Rule Based Approach - based model and algorithm, achieving an impressive accuracy of 86.28\%. |
  - A Hybrid Machine Transliteration Model Based on Multi-source Encoder–Decoder Framework: English to Manipuri - decoder models for multi-source framework, demonstrated through experiments on English to Manipuri transliteration task, showcasing significant performance improvement over its phoneme and grapheme counterparts. |
  - Manipuri Transliteration from Bengali Script to Meitei Mayek: A Rule Based Approach - based model and algorithm, achieving an impressive accuracy of 86.28\%. |
  - A Hybrid Machine Transliteration Model Based on Multi-source Encoder–Decoder Framework: English to Manipuri - decoder models for multi-source framework, demonstrated through experiments on English to Manipuri transliteration task, showcasing significant performance improvement over its phoneme and grapheme counterparts. |
  - Manipuri Transliteration from Bengali Script to Meitei Mayek: A Rule Based Approach - based model and algorithm, achieving an impressive accuracy of 86.28\%. |
  - A Hybrid Machine Transliteration Model Based on Multi-source Encoder–Decoder Framework: English to Manipuri - decoder models for multi-source framework, demonstrated through experiments on English to Manipuri transliteration task, showcasing significant performance improvement over its phoneme and grapheme counterparts. |
  - Manipuri Transliteration from Bengali Script to Meitei Mayek: A Rule Based Approach - based model and algorithm, achieving an impressive accuracy of 86.28\%. |
  - Manipuri Transliteration from Bengali Script to Meitei Mayek: A Rule Based Approach - based model and algorithm, achieving an impressive accuracy of 86.28\%. |
  - A Hybrid Machine Transliteration Model Based on Multi-source Encoder–Decoder Framework: English to Manipuri - decoder models for multi-source framework, demonstrated through experiments on English to Manipuri transliteration task, showcasing significant performance improvement over its phoneme and grapheme counterparts. |
  - Manipuri Transliteration from Bengali Script to Meitei Mayek: A Rule Based Approach - based model and algorithm, achieving an impressive accuracy of 86.28\%. |
  - A Hybrid Machine Transliteration Model Based on Multi-source Encoder–Decoder Framework: English to Manipuri - decoder models for multi-source framework, demonstrated through experiments on English to Manipuri transliteration task, showcasing significant performance improvement over its phoneme and grapheme counterparts. |
  - Manipuri Transliteration from Bengali Script to Meitei Mayek: A Rule Based Approach - based model and algorithm, achieving an impressive accuracy of 86.28\%. |
  - Manipuri Transliteration from Bengali Script to Meitei Mayek: A Rule Based Approach - based model and algorithm, achieving an impressive accuracy of 86.28\%. |
  - A Hybrid Machine Transliteration Model Based on Multi-source Encoder–Decoder Framework: English to Manipuri - decoder models for multi-source framework, demonstrated through experiments on English to Manipuri transliteration task, showcasing significant performance improvement over its phoneme and grapheme counterparts. |
  - Manipuri Transliteration from Bengali Script to Meitei Mayek: A Rule Based Approach - based model and algorithm, achieving an impressive accuracy of 86.28\%. |
  - Manipuri Transliteration from Bengali Script to Meitei Mayek: A Rule Based Approach - based model and algorithm, achieving an impressive accuracy of 86.28\%. |
  - A Hybrid Machine Transliteration Model Based on Multi-source Encoder–Decoder Framework: English to Manipuri - decoder models for multi-source framework, demonstrated through experiments on English to Manipuri transliteration task, showcasing significant performance improvement over its phoneme and grapheme counterparts. |
  - Manipuri Transliteration from Bengali Script to Meitei Mayek: A Rule Based Approach - based model and algorithm, achieving an impressive accuracy of 86.28\%. |
  - A Hybrid Machine Transliteration Model Based on Multi-source Encoder–Decoder Framework: English to Manipuri - decoder models for multi-source framework, demonstrated through experiments on English to Manipuri transliteration task, showcasing significant performance improvement over its phoneme and grapheme counterparts. |
  - Manipuri Transliteration from Bengali Script to Meitei Mayek: A Rule Based Approach - based model and algorithm, achieving an impressive accuracy of 86.28\%. |
  - A Hybrid Machine Transliteration Model Based on Multi-source Encoder–Decoder Framework: English to Manipuri - decoder models for multi-source framework, demonstrated through experiments on English to Manipuri transliteration task, showcasing significant performance improvement over its phoneme and grapheme counterparts. |
  - Manipuri Transliteration from Bengali Script to Meitei Mayek: A Rule Based Approach - based model and algorithm, achieving an impressive accuracy of 86.28\%. |
  - A Hybrid Machine Transliteration Model Based on Multi-source Encoder–Decoder Framework: English to Manipuri - decoder models for multi-source framework, demonstrated through experiments on English to Manipuri transliteration task, showcasing significant performance improvement over its phoneme and grapheme counterparts. |
  - Manipuri Transliteration from Bengali Script to Meitei Mayek: A Rule Based Approach - based model and algorithm, achieving an impressive accuracy of 86.28\%. |
  - A Hybrid Machine Transliteration Model Based on Multi-source Encoder–Decoder Framework: English to Manipuri - decoder models for multi-source framework, demonstrated through experiments on English to Manipuri transliteration task, showcasing significant performance improvement over its phoneme and grapheme counterparts. |
  - Manipuri Transliteration from Bengali Script to Meitei Mayek: A Rule Based Approach - based model and algorithm, achieving an impressive accuracy of 86.28\%. |
  - Manipuri Transliteration from Bengali Script to Meitei Mayek: A Rule Based Approach - based model and algorithm, achieving an impressive accuracy of 86.28\%. |
  - A Hybrid Machine Transliteration Model Based on Multi-source Encoder–Decoder Framework: English to Manipuri - decoder models for multi-source framework, demonstrated through experiments on English to Manipuri transliteration task, showcasing significant performance improvement over its phoneme and grapheme counterparts. |
  - Manipuri Transliteration from Bengali Script to Meitei Mayek: A Rule Based Approach - based model and algorithm, achieving an impressive accuracy of 86.28\%. |
  - Manipuri Transliteration from Bengali Script to Meitei Mayek: A Rule Based Approach - based model and algorithm, achieving an impressive accuracy of 86.28\%. |
  - A Hybrid Machine Transliteration Model Based on Multi-source Encoder–Decoder Framework: English to Manipuri - decoder models for multi-source framework, demonstrated through experiments on English to Manipuri transliteration task, showcasing significant performance improvement over its phoneme and grapheme counterparts. |
  - Manipuri Transliteration from Bengali Script to Meitei Mayek: A Rule Based Approach - based model and algorithm, achieving an impressive accuracy of 86.28\%. |
  - A Hybrid Machine Transliteration Model Based on Multi-source Encoder–Decoder Framework: English to Manipuri - decoder models for multi-source framework, demonstrated through experiments on English to Manipuri transliteration task, showcasing significant performance improvement over its phoneme and grapheme counterparts. |
  - Manipuri Transliteration from Bengali Script to Meitei Mayek: A Rule Based Approach - based model and algorithm, achieving an impressive accuracy of 86.28\%. |
  - A Hybrid Machine Transliteration Model Based on Multi-source Encoder–Decoder Framework: English to Manipuri - decoder models for multi-source framework, demonstrated through experiments on English to Manipuri transliteration task, showcasing significant performance improvement over its phoneme and grapheme counterparts. |
  - A Hybrid Machine Transliteration Model Based on Multi-source Encoder–Decoder Framework: English to Manipuri - decoder models for multi-source framework, demonstrated through experiments on English to Manipuri transliteration task, showcasing significant performance improvement over its phoneme and grapheme counterparts. |
  - Manipuri Transliteration from Bengali Script to Meitei Mayek: A Rule Based Approach - based model and algorithm, achieving an impressive accuracy of 86.28\%. |
  - Manipuri Transliteration from Bengali Script to Meitei Mayek: A Rule Based Approach - based model and algorithm, achieving an impressive accuracy of 86.28\%. |
  - A Hybrid Machine Transliteration Model Based on Multi-source Encoder–Decoder Framework: English to Manipuri - decoder models for multi-source framework, demonstrated through experiments on English to Manipuri transliteration task, showcasing significant performance improvement over its phoneme and grapheme counterparts. |
  - Manipuri Transliteration from Bengali Script to Meitei Mayek: A Rule Based Approach - based model and algorithm, achieving an impressive accuracy of 86.28\%. |
  - Manipuri Transliteration from Bengali Script to Meitei Mayek: A Rule Based Approach - based model and algorithm, achieving an impressive accuracy of 86.28\%. |
  - A Hybrid Machine Transliteration Model Based on Multi-source Encoder–Decoder Framework: English to Manipuri - decoder models for multi-source framework, demonstrated through experiments on English to Manipuri transliteration task, showcasing significant performance improvement over its phoneme and grapheme counterparts. |
  - Manipuri Transliteration from Bengali Script to Meitei Mayek: A Rule Based Approach - based model and algorithm, achieving an impressive accuracy of 86.28\%. |
  - A Hybrid Machine Transliteration Model Based on Multi-source Encoder–Decoder Framework: English to Manipuri - decoder models for multi-source framework, demonstrated through experiments on English to Manipuri transliteration task, showcasing significant performance improvement over its phoneme and grapheme counterparts. |
  - Manipuri Transliteration from Bengali Script to Meitei Mayek: A Rule Based Approach - based model and algorithm, achieving an impressive accuracy of 86.28\%. |
  - A Hybrid Machine Transliteration Model Based on Multi-source Encoder–Decoder Framework: English to Manipuri - decoder models for multi-source framework, demonstrated through experiments on English to Manipuri transliteration task, showcasing significant performance improvement over its phoneme and grapheme counterparts. |
  - Manipuri Transliteration from Bengali Script to Meitei Mayek: A Rule Based Approach - based model and algorithm, achieving an impressive accuracy of 86.28\%. |
  - Manipuri Transliteration from Bengali Script to Meitei Mayek: A Rule Based Approach - based model and algorithm, achieving an impressive accuracy of 86.28\%. |
  - A Hybrid Machine Transliteration Model Based on Multi-source Encoder–Decoder Framework: English to Manipuri - decoder models for multi-source framework, demonstrated through experiments on English to Manipuri transliteration task, showcasing significant performance improvement over its phoneme and grapheme counterparts. |
  - Manipuri Transliteration from Bengali Script to Meitei Mayek: A Rule Based Approach - based model and algorithm, achieving an impressive accuracy of 86.28\%. |
  - A Hybrid Machine Transliteration Model Based on Multi-source Encoder–Decoder Framework: English to Manipuri - decoder models for multi-source framework, demonstrated through experiments on English to Manipuri transliteration task, showcasing significant performance improvement over its phoneme and grapheme counterparts. |
  - Manipuri Transliteration from Bengali Script to Meitei Mayek: A Rule Based Approach - based model and algorithm, achieving an impressive accuracy of 86.28\%. |
  - Manipuri Transliteration from Bengali Script to Meitei Mayek: A Rule Based Approach - based model and algorithm, achieving an impressive accuracy of 86.28\%. |
  - Manipuri Transliteration from Bengali Script to Meitei Mayek: A Rule Based Approach - based model and algorithm, achieving an impressive accuracy of 86.28\%. |
  - A Hybrid Machine Transliteration Model Based on Multi-source Encoder–Decoder Framework: English to Manipuri - decoder models for multi-source framework, demonstrated through experiments on English to Manipuri transliteration task, showcasing significant performance improvement over its phoneme and grapheme counterparts. |
  - Manipuri Transliteration from Bengali Script to Meitei Mayek: A Rule Based Approach - based model and algorithm, achieving an impressive accuracy of 86.28\%. |
  - A Hybrid Machine Transliteration Model Based on Multi-source Encoder–Decoder Framework: English to Manipuri - decoder models for multi-source framework, demonstrated through experiments on English to Manipuri transliteration task, showcasing significant performance improvement over its phoneme and grapheme counterparts. |
  - Manipuri Transliteration from Bengali Script to Meitei Mayek: A Rule Based Approach - based model and algorithm, achieving an impressive accuracy of 86.28\%. |
  - Manipuri Transliteration from Bengali Script to Meitei Mayek: A Rule Based Approach - based model and algorithm, achieving an impressive accuracy of 86.28\%. |
  - A Transliteration of CRF based Manipuri POS Tagging
  - Manipuri Transliteration from Bengali Script to Meitei Mayek: A Rule Based Approach - based model and algorithm, achieving an impressive accuracy of 86.28\%. |
  - Manipuri Transliteration from Bengali Script to Meitei Mayek: A Rule Based Approach - based model and algorithm, achieving an impressive accuracy of 86.28\%. |
  - Manipuri Transliteration from Bengali Script to Meitei Mayek: A Rule Based Approach - based model and algorithm, achieving an impressive accuracy of 86.28\%. |
  - Bidirectional Bengali Script and Meetei Mayek Transliteration of Web Based Manipuri News Corpus - based transliteration approach between Bengali and Meetei Mayek scripts for Manipuri text, emphasizing the significance of linguistic rule integration leveraging Manipuri's monosyllabic nature, achieving higher precision and recall than statistical methods for Bengali to Meetei Mayek transliteration, while statistical approaches outperform rule-based methods for the reverse transliteration. |
  - A Hybrid Machine Transliteration Model Based on Multi-source Encoder–Decoder Framework: English to Manipuri - decoder models for multi-source framework, demonstrated through experiments on English to Manipuri transliteration task, showcasing significant performance improvement over its phoneme and grapheme counterparts. |
  - Manipuri Transliteration from Bengali Script to Meitei Mayek: A Rule Based Approach - based model and algorithm, achieving an impressive accuracy of 86.28\%. |
  - Manipuri Transliteration from Bengali Script to Meitei Mayek: A Rule Based Approach - based model and algorithm, achieving an impressive accuracy of 86.28\%. |
  - A Hybrid Machine Transliteration Model Based on Multi-source Encoder–Decoder Framework: English to Manipuri - decoder models for multi-source framework, demonstrated through experiments on English to Manipuri transliteration task, showcasing significant performance improvement over its phoneme and grapheme counterparts. |
  - Manipuri Transliteration from Bengali Script to Meitei Mayek: A Rule Based Approach - based model and algorithm, achieving an impressive accuracy of 86.28\%. |
  - Manipuri Transliteration from Bengali Script to Meitei Mayek: A Rule Based Approach - based model and algorithm, achieving an impressive accuracy of 86.28\%. |
  - A Hybrid Machine Transliteration Model Based on Multi-source Encoder–Decoder Framework: English to Manipuri - decoder models for multi-source framework, demonstrated through experiments on English to Manipuri transliteration task, showcasing significant performance improvement over its phoneme and grapheme counterparts. |
  - Manipuri Transliteration from Bengali Script to Meitei Mayek: A Rule Based Approach - based model and algorithm, achieving an impressive accuracy of 86.28\%. |
  - Manipuri Transliteration from Bengali Script to Meitei Mayek: A Rule Based Approach - based model and algorithm, achieving an impressive accuracy of 86.28\%. |
  - A Hybrid Machine Transliteration Model Based on Multi-source Encoder–Decoder Framework: English to Manipuri - decoder models for multi-source framework, demonstrated through experiments on English to Manipuri transliteration task, showcasing significant performance improvement over its phoneme and grapheme counterparts. |
  - Manipuri Transliteration from Bengali Script to Meitei Mayek: A Rule Based Approach - based model and algorithm, achieving an impressive accuracy of 86.28\%. |
  - A Hybrid Machine Transliteration Model Based on Multi-source Encoder–Decoder Framework: English to Manipuri - decoder models for multi-source framework, demonstrated through experiments on English to Manipuri transliteration task, showcasing significant performance improvement over its phoneme and grapheme counterparts. |
  - Manipuri Transliteration from Bengali Script to Meitei Mayek: A Rule Based Approach - based model and algorithm, achieving an impressive accuracy of 86.28\%. |
  - A Hybrid Machine Transliteration Model Based on Multi-source Encoder–Decoder Framework: English to Manipuri - decoder models for multi-source framework, demonstrated through experiments on English to Manipuri transliteration task, showcasing significant performance improvement over its phoneme and grapheme counterparts. |
  - Manipuri Transliteration from Bengali Script to Meitei Mayek: A Rule Based Approach - based model and algorithm, achieving an impressive accuracy of 86.28\%. |
  - A Hybrid Machine Transliteration Model Based on Multi-source Encoder–Decoder Framework: English to Manipuri - decoder models for multi-source framework, demonstrated through experiments on English to Manipuri transliteration task, showcasing significant performance improvement over its phoneme and grapheme counterparts. |
  - Manipuri Transliteration from Bengali Script to Meitei Mayek: A Rule Based Approach - based model and algorithm, achieving an impressive accuracy of 86.28\%. |
  - Manipuri Transliteration from Bengali Script to Meitei Mayek: A Rule Based Approach - based model and algorithm, achieving an impressive accuracy of 86.28\%. |
  - Manipuri Transliteration from Bengali Script to Meitei Mayek: A Rule Based Approach - based model and algorithm, achieving an impressive accuracy of 86.28\%. |
  - A Hybrid Machine Transliteration Model Based on Multi-source Encoder–Decoder Framework: English to Manipuri - decoder models for multi-source framework, demonstrated through experiments on English to Manipuri transliteration task, showcasing significant performance improvement over its phoneme and grapheme counterparts. |
  - Manipuri Transliteration from Bengali Script to Meitei Mayek: A Rule Based Approach - based model and algorithm, achieving an impressive accuracy of 86.28\%. |
  - A Hybrid Machine Transliteration Model Based on Multi-source Encoder–Decoder Framework: English to Manipuri - decoder models for multi-source framework, demonstrated through experiments on English to Manipuri transliteration task, showcasing significant performance improvement over its phoneme and grapheme counterparts. |
  - Manipuri Transliteration from Bengali Script to Meitei Mayek: A Rule Based Approach - based model and algorithm, achieving an impressive accuracy of 86.28\%. |
  - A Hybrid Machine Transliteration Model Based on Multi-source Encoder–Decoder Framework: English to Manipuri - decoder models for multi-source framework, demonstrated through experiments on English to Manipuri transliteration task, showcasing significant performance improvement over its phoneme and grapheme counterparts. |
  - Manipuri Transliteration from Bengali Script to Meitei Mayek: A Rule Based Approach - based model and algorithm, achieving an impressive accuracy of 86.28\%. |
  - A Hybrid Machine Transliteration Model Based on Multi-source Encoder–Decoder Framework: English to Manipuri - decoder models for multi-source framework, demonstrated through experiments on English to Manipuri transliteration task, showcasing significant performance improvement over its phoneme and grapheme counterparts. |
  - Manipuri Transliteration from Bengali Script to Meitei Mayek: A Rule Based Approach - based model and algorithm, achieving an impressive accuracy of 86.28\%. |
  - A Hybrid Machine Transliteration Model Based on Multi-source Encoder–Decoder Framework: English to Manipuri - decoder models for multi-source framework, demonstrated through experiments on English to Manipuri transliteration task, showcasing significant performance improvement over its phoneme and grapheme counterparts. |
  - Manipuri Transliteration from Bengali Script to Meitei Mayek: A Rule Based Approach - based model and algorithm, achieving an impressive accuracy of 86.28\%. |
  - A Hybrid Machine Transliteration Model Based on Multi-source Encoder–Decoder Framework: English to Manipuri - decoder models for multi-source framework, demonstrated through experiments on English to Manipuri transliteration task, showcasing significant performance improvement over its phoneme and grapheme counterparts. |
  - Manipuri Transliteration from Bengali Script to Meitei Mayek: A Rule Based Approach - based model and algorithm, achieving an impressive accuracy of 86.28\%. |
  - A Hybrid Machine Transliteration Model Based on Multi-source Encoder–Decoder Framework: English to Manipuri - decoder models for multi-source framework, demonstrated through experiments on English to Manipuri transliteration task, showcasing significant performance improvement over its phoneme and grapheme counterparts. |
  - Manipuri Transliteration from Bengali Script to Meitei Mayek: A Rule Based Approach - based model and algorithm, achieving an impressive accuracy of 86.28\%. |
  - Manipuri Transliteration from Bengali Script to Meitei Mayek: A Rule Based Approach - based model and algorithm, achieving an impressive accuracy of 86.28\%. |
  - A Hybrid Machine Transliteration Model Based on Multi-source Encoder–Decoder Framework: English to Manipuri - decoder models for multi-source framework, demonstrated through experiments on English to Manipuri transliteration task, showcasing significant performance improvement over its phoneme and grapheme counterparts. |
  - Manipuri Transliteration from Bengali Script to Meitei Mayek: A Rule Based Approach - based model and algorithm, achieving an impressive accuracy of 86.28\%. |
  - A Hybrid Machine Transliteration Model Based on Multi-source Encoder–Decoder Framework: English to Manipuri - decoder models for multi-source framework, demonstrated through experiments on English to Manipuri transliteration task, showcasing significant performance improvement over its phoneme and grapheme counterparts. |
  - Manipuri Transliteration from Bengali Script to Meitei Mayek: A Rule Based Approach - based model and algorithm, achieving an impressive accuracy of 86.28\%. |
  - A Hybrid Machine Transliteration Model Based on Multi-source Encoder–Decoder Framework: English to Manipuri - decoder models for multi-source framework, demonstrated through experiments on English to Manipuri transliteration task, showcasing significant performance improvement over its phoneme and grapheme counterparts. |
  - Manipuri Transliteration from Bengali Script to Meitei Mayek: A Rule Based Approach - based model and algorithm, achieving an impressive accuracy of 86.28\%. |
  - A Hybrid Machine Transliteration Model Based on Multi-source Encoder–Decoder Framework: English to Manipuri - decoder models for multi-source framework, demonstrated through experiments on English to Manipuri transliteration task, showcasing significant performance improvement over its phoneme and grapheme counterparts. |
Index
- POS Tagging
  - Transliterated SVM Based Manipuri POS Tagging
  - Will the Identification of Reduplicated Multiword Expression (RMWE) Improve the Performance of SVM Based Manipuri POS Tagging? - Score increase from 77.67\% to 79.61\%. |
  - Transliterated SVM Based Manipuri POS Tagging
  - Will the Identification of Reduplicated Multiword Expression (RMWE) Improve the Performance of SVM Based Manipuri POS Tagging? - Score increase from 77.67\% to 79.61\%. |
  - Transliterated SVM Based Manipuri POS Tagging
  - Will the Identification of Reduplicated Multiword Expression (RMWE) Improve the Performance of SVM Based Manipuri POS Tagging? - Score increase from 77.67\% to 79.61\%. |
  - Transliterated SVM Based Manipuri POS Tagging
  - Will the Identification of Reduplicated Multiword Expression (RMWE) Improve the Performance of SVM Based Manipuri POS Tagging? - Score increase from 77.67\% to 79.61\%. |
  - Transliterated SVM Based Manipuri POS Tagging
  - Will the Identification of Reduplicated Multiword Expression (RMWE) Improve the Performance of SVM Based Manipuri POS Tagging? - Score increase from 77.67\% to 79.61\%. |
  - Transliterated SVM Based Manipuri POS Tagging
  - Will the Identification of Reduplicated Multiword Expression (RMWE) Improve the Performance of SVM Based Manipuri POS Tagging? - Score increase from 77.67\% to 79.61\%. |
  - Transliterated SVM Based Manipuri POS Tagging
  - Will the Identification of Reduplicated Multiword Expression (RMWE) Improve the Performance of SVM Based Manipuri POS Tagging? - Score increase from 77.67\% to 79.61\%. |
  - Transliterated SVM Based Manipuri POS Tagging
  - Will the Identification of Reduplicated Multiword Expression (RMWE) Improve the Performance of SVM Based Manipuri POS Tagging? - Score increase from 77.67\% to 79.61\%. |
  - Transliterated SVM Based Manipuri POS Tagging
  - Will the Identification of Reduplicated Multiword Expression (RMWE) Improve the Performance of SVM Based Manipuri POS Tagging? - Score increase from 77.67\% to 79.61\%. |
  - Transliterated SVM Based Manipuri POS Tagging
  - Will the Identification of Reduplicated Multiword Expression (RMWE) Improve the Performance of SVM Based Manipuri POS Tagging? - Score increase from 77.67\% to 79.61\%. |
  - Transliterated SVM Based Manipuri POS Tagging
  - Will the Identification of Reduplicated Multiword Expression (RMWE) Improve the Performance of SVM Based Manipuri POS Tagging? - Score increase from 77.67\% to 79.61\%. |
  - Transliterated SVM Based Manipuri POS Tagging
  - Will the Identification of Reduplicated Multiword Expression (RMWE) Improve the Performance of SVM Based Manipuri POS Tagging? - Score increase from 77.67\% to 79.61\%. |
  - Transliterated SVM Based Manipuri POS Tagging
  - Will the Identification of Reduplicated Multiword Expression (RMWE) Improve the Performance of SVM Based Manipuri POS Tagging? - Score increase from 77.67\% to 79.61\%. |
  - Transliterated SVM Based Manipuri POS Tagging
  - Will the Identification of Reduplicated Multiword Expression (RMWE) Improve the Performance of SVM Based Manipuri POS Tagging? - Score increase from 77.67\% to 79.61\%. |
  - Transliterated SVM Based Manipuri POS Tagging
  - Will the Identification of Reduplicated Multiword Expression (RMWE) Improve the Performance of SVM Based Manipuri POS Tagging? - Score increase from 77.67\% to 79.61\%. |
  - Transliterated SVM Based Manipuri POS Tagging
  - Will the Identification of Reduplicated Multiword Expression (RMWE) Improve the Performance of SVM Based Manipuri POS Tagging? - Score increase from 77.67\% to 79.61\%. |
  - Transliterated SVM Based Manipuri POS Tagging
  - Will the Identification of Reduplicated Multiword Expression (RMWE) Improve the Performance of SVM Based Manipuri POS Tagging? - Score increase from 77.67\% to 79.61\%. |
  - Transliterated SVM Based Manipuri POS Tagging
  - Will the Identification of Reduplicated Multiword Expression (RMWE) Improve the Performance of SVM Based Manipuri POS Tagging? - Score increase from 77.67\% to 79.61\%. |
  - Transliterated SVM Based Manipuri POS Tagging
  - Will the Identification of Reduplicated Multiword Expression (RMWE) Improve the Performance of SVM Based Manipuri POS Tagging? - Score increase from 77.67\% to 79.61\%. |
  - Will the Identification of Reduplicated Multiword Expression (RMWE) Improve the Performance of SVM Based Manipuri POS Tagging? - Score increase from 77.67\% to 79.61\%. |
  - Transliterated SVM Based Manipuri POS Tagging
  - Transliterated SVM Based Manipuri POS Tagging
  - Will the Identification of Reduplicated Multiword Expression (RMWE) Improve the Performance of SVM Based Manipuri POS Tagging? - Score increase from 77.67\% to 79.61\%. |
  - Transliterated SVM Based Manipuri POS Tagging
  - Will the Identification of Reduplicated Multiword Expression (RMWE) Improve the Performance of SVM Based Manipuri POS Tagging? - Score increase from 77.67\% to 79.61\%. |
  - Transliterated SVM Based Manipuri POS Tagging
  - Will the Identification of Reduplicated Multiword Expression (RMWE) Improve the Performance of SVM Based Manipuri POS Tagging? - Score increase from 77.67\% to 79.61\%. |
  - Transliterated SVM Based Manipuri POS Tagging
  - Will the Identification of Reduplicated Multiword Expression (RMWE) Improve the Performance of SVM Based Manipuri POS Tagging? - Score increase from 77.67\% to 79.61\%. |
  - Transliterated SVM Based Manipuri POS Tagging
  - Will the Identification of Reduplicated Multiword Expression (RMWE) Improve the Performance of SVM Based Manipuri POS Tagging? - Score increase from 77.67\% to 79.61\%. |
  - Transliterated SVM Based Manipuri POS Tagging
  - Will the Identification of Reduplicated Multiword Expression (RMWE) Improve the Performance of SVM Based Manipuri POS Tagging? - Score increase from 77.67\% to 79.61\%. |
  - Will the Identification of Reduplicated Multiword Expression (RMWE) Improve the Performance of SVM Based Manipuri POS Tagging? - Score increase from 77.67\% to 79.61\%. |
  - Transliterated SVM Based Manipuri POS Tagging
  - Transliterated SVM Based Manipuri POS Tagging
  - Will the Identification of Reduplicated Multiword Expression (RMWE) Improve the Performance of SVM Based Manipuri POS Tagging? - Score increase from 77.67\% to 79.61\%. |
  - Transliterated SVM Based Manipuri POS Tagging
  - Will the Identification of Reduplicated Multiword Expression (RMWE) Improve the Performance of SVM Based Manipuri POS Tagging? - Score increase from 77.67\% to 79.61\%. |
  - Transliterated SVM Based Manipuri POS Tagging
  - Will the Identification of Reduplicated Multiword Expression (RMWE) Improve the Performance of SVM Based Manipuri POS Tagging? - Score increase from 77.67\% to 79.61\%. |
  - Transliterated SVM Based Manipuri POS Tagging
  - Will the Identification of Reduplicated Multiword Expression (RMWE) Improve the Performance of SVM Based Manipuri POS Tagging? - Score increase from 77.67\% to 79.61\%. |
  - Transliterated SVM Based Manipuri POS Tagging
  - Will the Identification of Reduplicated Multiword Expression (RMWE) Improve the Performance of SVM Based Manipuri POS Tagging? - Score increase from 77.67\% to 79.61\%. |
  - Transliterated SVM Based Manipuri POS Tagging
  - Will the Identification of Reduplicated Multiword Expression (RMWE) Improve the Performance of SVM Based Manipuri POS Tagging? - Score increase from 77.67\% to 79.61\%. |
  - Transliterated SVM Based Manipuri POS Tagging
  - Will the Identification of Reduplicated Multiword Expression (RMWE) Improve the Performance of SVM Based Manipuri POS Tagging? - Score increase from 77.67\% to 79.61\%. |
  - Transliterated SVM Based Manipuri POS Tagging
  - Will the Identification of Reduplicated Multiword Expression (RMWE) Improve the Performance of SVM Based Manipuri POS Tagging? - Score increase from 77.67\% to 79.61\%. |
  - Transliterated SVM Based Manipuri POS Tagging
  - Will the Identification of Reduplicated Multiword Expression (RMWE) Improve the Performance of SVM Based Manipuri POS Tagging? - Score increase from 77.67\% to 79.61\%. |
  - Transliterated SVM Based Manipuri POS Tagging
  - Will the Identification of Reduplicated Multiword Expression (RMWE) Improve the Performance of SVM Based Manipuri POS Tagging? - Score increase from 77.67\% to 79.61\%. |
  - Transliterated SVM Based Manipuri POS Tagging
  - Will the Identification of Reduplicated Multiword Expression (RMWE) Improve the Performance of SVM Based Manipuri POS Tagging? - Score increase from 77.67\% to 79.61\%. |
  - Morphology Driven Manipuri POS Tagger - driven POS tagger for Manipuri language, utilizing dictionaries of root words, prefixes, and suffixes to achieve an accuracy of 69\% on 3784 sentences containing 10917 unique words. |
  - Manipuri POS Tagging using CRF and SVM: A Language Independent Approach
  - CRF Based POS Tagging of Manipuri - measure of 73.68\% |
  - Part of Speech Tagging in Manipuri: A Rule-based Approach - based Part of Speech (POS) tagger for Manipuri, employing hand-written linguistic rules and affix stripping technique to handle the challenges of classifying the lexical categories. |
  - Improvement of CRF Based Manipuri POS Tagger by Using Reduplicated MWE (RMWE) - measure of 77.14\% by incorporating Reduplicated Multiword Expression (RMWE) as an additional feature. |
  - Transliterated SVM Based Manipuri POS Tagging
  - Will the Identification of Reduplicated Multiword Expression (RMWE) Improve the Performance of SVM Based Manipuri POS Tagging? - Score increase from 77.67\% to 79.61\%. |
  - Part of Speech Tagging in Manipuri with Hidden Markov Model - based tagger as the tagged corpus. |
  - Transliterated SVM Based Manipuri POS Tagging
  - Will the Identification of Reduplicated Multiword Expression (RMWE) Improve the Performance of SVM Based Manipuri POS Tagging? - Score increase from 77.67\% to 79.61\%. |
  - Transliterated SVM Based Manipuri POS Tagging
  - Will the Identification of Reduplicated Multiword Expression (RMWE) Improve the Performance of SVM Based Manipuri POS Tagging? - Score increase from 77.67\% to 79.61\%. |
  - Transliterated SVM Based Manipuri POS Tagging
  - Will the Identification of Reduplicated Multiword Expression (RMWE) Improve the Performance of SVM Based Manipuri POS Tagging? - Score increase from 77.67\% to 79.61\%. |
  - Transliterated SVM Based Manipuri POS Tagging
  - Will the Identification of Reduplicated Multiword Expression (RMWE) Improve the Performance of SVM Based Manipuri POS Tagging? - Score increase from 77.67\% to 79.61\%. |
  - Transliterated SVM Based Manipuri POS Tagging
  - Will the Identification of Reduplicated Multiword Expression (RMWE) Improve the Performance of SVM Based Manipuri POS Tagging? - Score increase from 77.67\% to 79.61\%. |
  - Transliterated SVM Based Manipuri POS Tagging
  - Will the Identification of Reduplicated Multiword Expression (RMWE) Improve the Performance of SVM Based Manipuri POS Tagging? - Score increase from 77.67\% to 79.61\%. |
  - Transliterated SVM Based Manipuri POS Tagging
  - Will the Identification of Reduplicated Multiword Expression (RMWE) Improve the Performance of SVM Based Manipuri POS Tagging? - Score increase from 77.67\% to 79.61\%. |
  - Transliterated SVM Based Manipuri POS Tagging
  - Will the Identification of Reduplicated Multiword Expression (RMWE) Improve the Performance of SVM Based Manipuri POS Tagging? - Score increase from 77.67\% to 79.61\%. |
  - Transliterated SVM Based Manipuri POS Tagging
  - Will the Identification of Reduplicated Multiword Expression (RMWE) Improve the Performance of SVM Based Manipuri POS Tagging? - Score increase from 77.67\% to 79.61\%. |
  - Transliterated SVM Based Manipuri POS Tagging
  - Will the Identification of Reduplicated Multiword Expression (RMWE) Improve the Performance of SVM Based Manipuri POS Tagging? - Score increase from 77.67\% to 79.61\%. |
  - Transliterated SVM Based Manipuri POS Tagging
  - Will the Identification of Reduplicated Multiword Expression (RMWE) Improve the Performance of SVM Based Manipuri POS Tagging? - Score increase from 77.67\% to 79.61\%. |
  - Transliterated SVM Based Manipuri POS Tagging
  - Will the Identification of Reduplicated Multiword Expression (RMWE) Improve the Performance of SVM Based Manipuri POS Tagging? - Score increase from 77.67\% to 79.61\%. |
  - Will the Identification of Reduplicated Multiword Expression (RMWE) Improve the Performance of SVM Based Manipuri POS Tagging? - Score increase from 77.67\% to 79.61\%. |
  - Part of Speech Tagging in Manipuri with Hidden Markov Model - based tagger as the tagged corpus. |
  - Transliterated SVM Based Manipuri POS Tagging
  - Transliterated SVM Based Manipuri POS Tagging
  - Will the Identification of Reduplicated Multiword Expression (RMWE) Improve the Performance of SVM Based Manipuri POS Tagging? - Score increase from 77.67\% to 79.61\%. |
  - Transliterated SVM Based Manipuri POS Tagging
  - Will the Identification of Reduplicated Multiword Expression (RMWE) Improve the Performance of SVM Based Manipuri POS Tagging? - Score increase from 77.67\% to 79.61\%. |
  - Transliterated SVM Based Manipuri POS Tagging
  - Will the Identification of Reduplicated Multiword Expression (RMWE) Improve the Performance of SVM Based Manipuri POS Tagging? - Score increase from 77.67\% to 79.61\%. |
  - Transliterated SVM Based Manipuri POS Tagging
  - Transliterated SVM Based Manipuri POS Tagging
  - Will the Identification of Reduplicated Multiword Expression (RMWE) Improve the Performance of SVM Based Manipuri POS Tagging? - Score increase from 77.67\% to 79.61\%. |
  - Will the Identification of Reduplicated Multiword Expression (RMWE) Improve the Performance of SVM Based Manipuri POS Tagging? - Score increase from 77.67\% to 79.61\%. |
  - SVM based Manipuri POS tagging using SVM based identified reduplicated MWE (RMWE) - measure of 88.99\%, and subsequently utilizes these identified RMWE as features in SVM-based POS tagging, yielding a recall of 71.15\%, precision of 83.15\%, and F-measure of 76.68\%. |
  - Transliterated SVM Based Manipuri POS Tagging
  - Will the Identification of Reduplicated Multiword Expression (RMWE) Improve the Performance of SVM Based Manipuri POS Tagging? - Score increase from 77.67\% to 79.61\%. |
  - Transliterated SVM Based Manipuri POS Tagging
  - Will the Identification of Reduplicated Multiword Expression (RMWE) Improve the Performance of SVM Based Manipuri POS Tagging? - Score increase from 77.67\% to 79.61\%. |
  - Transliterated SVM Based Manipuri POS Tagging
  - Will the Identification of Reduplicated Multiword Expression (RMWE) Improve the Performance of SVM Based Manipuri POS Tagging? - Score increase from 77.67\% to 79.61\%. |
  - Transliterated SVM Based Manipuri POS Tagging
  - Will the Identification of Reduplicated Multiword Expression (RMWE) Improve the Performance of SVM Based Manipuri POS Tagging? - Score increase from 77.67\% to 79.61\%. |
- Named Entity Recognition
  - Named Entity Recognition in Manipuri: A Hybrid Approach - based techniques, achieving Recall, Precision, and F-score of 92.26\%, 94.27\%, and 93.3\% respectively. |
  - BiLSTM-CRF Manipuri NER with Character-Level Word Representation - level word representation and word embedding, augmented by a Conditional Random Field (CRF) classifier, achieving an F-Score measure of approximately 98.19\% with RMSprop Gradient Descent (GD) optimizer, and an average clustering accuracy of 88.14\% for all NE classes. |
  - Named Entity Recognition in Manipuri: A Hybrid Approach - based techniques, achieving Recall, Precision, and F-score of 92.26\%, 94.27\%, and 93.3\% respectively. |
  - BiLSTM-CRF Manipuri NER with Character-Level Word Representation - level word representation and word embedding, augmented by a Conditional Random Field (CRF) classifier, achieving an F-Score measure of approximately 98.19\% with RMSprop Gradient Descent (GD) optimizer, and an average clustering accuracy of 88.14\% for all NE classes. |
  - Named Entity Recognition in Manipuri: A Hybrid Approach - based techniques, achieving Recall, Precision, and F-score of 92.26\%, 94.27\%, and 93.3\% respectively. |
  - BiLSTM-CRF Manipuri NER with Character-Level Word Representation - level word representation and word embedding, augmented by a Conditional Random Field (CRF) classifier, achieving an F-Score measure of approximately 98.19\% with RMSprop Gradient Descent (GD) optimizer, and an average clustering accuracy of 88.14\% for all NE classes. |
  - Named Entity Recognition in Manipuri: A Hybrid Approach - based techniques, achieving Recall, Precision, and F-score of 92.26\%, 94.27\%, and 93.3\% respectively. |
  - BiLSTM-CRF Manipuri NER with Character-Level Word Representation - level word representation and word embedding, augmented by a Conditional Random Field (CRF) classifier, achieving an F-Score measure of approximately 98.19\% with RMSprop Gradient Descent (GD) optimizer, and an average clustering accuracy of 88.14\% for all NE classes. |
  - Named Entity Recognition in Manipuri: A Hybrid Approach - based techniques, achieving Recall, Precision, and F-score of 92.26\%, 94.27\%, and 93.3\% respectively. |
  - BiLSTM-CRF Manipuri NER with Character-Level Word Representation - level word representation and word embedding, augmented by a Conditional Random Field (CRF) classifier, achieving an F-Score measure of approximately 98.19\% with RMSprop Gradient Descent (GD) optimizer, and an average clustering accuracy of 88.14\% for all NE classes. |
  - Named Entity Recognition in Manipuri: A Hybrid Approach - based techniques, achieving Recall, Precision, and F-score of 92.26\%, 94.27\%, and 93.3\% respectively. |
  - BiLSTM-CRF Manipuri NER with Character-Level Word Representation - level word representation and word embedding, augmented by a Conditional Random Field (CRF) classifier, achieving an F-Score measure of approximately 98.19\% with RMSprop Gradient Descent (GD) optimizer, and an average clustering accuracy of 88.14\% for all NE classes. |
  - Named Entity Recognition in Manipuri: A Hybrid Approach - based techniques, achieving Recall, Precision, and F-score of 92.26\%, 94.27\%, and 93.3\% respectively. |
  - BiLSTM-CRF Manipuri NER with Character-Level Word Representation - level word representation and word embedding, augmented by a Conditional Random Field (CRF) classifier, achieving an F-Score measure of approximately 98.19\% with RMSprop Gradient Descent (GD) optimizer, and an average clustering accuracy of 88.14\% for all NE classes. |
  - Named Entity Recognition in Manipuri: A Hybrid Approach - based techniques, achieving Recall, Precision, and F-score of 92.26\%, 94.27\%, and 93.3\% respectively. |
  - BiLSTM-CRF Manipuri NER with Character-Level Word Representation - level word representation and word embedding, augmented by a Conditional Random Field (CRF) classifier, achieving an F-Score measure of approximately 98.19\% with RMSprop Gradient Descent (GD) optimizer, and an average clustering accuracy of 88.14\% for all NE classes. |
  - Named Entity Recognition in Manipuri: A Hybrid Approach - based techniques, achieving Recall, Precision, and F-score of 92.26\%, 94.27\%, and 93.3\% respectively. |
  - BiLSTM-CRF Manipuri NER with Character-Level Word Representation - level word representation and word embedding, augmented by a Conditional Random Field (CRF) classifier, achieving an F-Score measure of approximately 98.19\% with RMSprop Gradient Descent (GD) optimizer, and an average clustering accuracy of 88.14\% for all NE classes. |
  - Named Entity Recognition in Manipuri: A Hybrid Approach - based techniques, achieving Recall, Precision, and F-score of 92.26\%, 94.27\%, and 93.3\% respectively. |
  - BiLSTM-CRF Manipuri NER with Character-Level Word Representation - level word representation and word embedding, augmented by a Conditional Random Field (CRF) classifier, achieving an F-Score measure of approximately 98.19\% with RMSprop Gradient Descent (GD) optimizer, and an average clustering accuracy of 88.14\% for all NE classes. |
  - Named Entity Recognition in Manipuri: A Hybrid Approach - based techniques, achieving Recall, Precision, and F-score of 92.26\%, 94.27\%, and 93.3\% respectively. |
  - BiLSTM-CRF Manipuri NER with Character-Level Word Representation - level word representation and word embedding, augmented by a Conditional Random Field (CRF) classifier, achieving an F-Score measure of approximately 98.19\% with RMSprop Gradient Descent (GD) optimizer, and an average clustering accuracy of 88.14\% for all NE classes. |
  - Named Entity Recognition in Manipuri: A Hybrid Approach - based techniques, achieving Recall, Precision, and F-score of 92.26\%, 94.27\%, and 93.3\% respectively. |
  - BiLSTM-CRF Manipuri NER with Character-Level Word Representation - level word representation and word embedding, augmented by a Conditional Random Field (CRF) classifier, achieving an F-Score measure of approximately 98.19\% with RMSprop Gradient Descent (GD) optimizer, and an average clustering accuracy of 88.14\% for all NE classes. |
  - Named Entity Recognition in Manipuri: A Hybrid Approach - based techniques, achieving Recall, Precision, and F-score of 92.26\%, 94.27\%, and 93.3\% respectively. |
  - BiLSTM-CRF Manipuri NER with Character-Level Word Representation - level word representation and word embedding, augmented by a Conditional Random Field (CRF) classifier, achieving an F-Score measure of approximately 98.19\% with RMSprop Gradient Descent (GD) optimizer, and an average clustering accuracy of 88.14\% for all NE classes. |
  - Named Entity Recognition in Manipuri: A Hybrid Approach - based techniques, achieving Recall, Precision, and F-score of 92.26\%, 94.27\%, and 93.3\% respectively. |
  - BiLSTM-CRF Manipuri NER with Character-Level Word Representation - level word representation and word embedding, augmented by a Conditional Random Field (CRF) classifier, achieving an F-Score measure of approximately 98.19\% with RMSprop Gradient Descent (GD) optimizer, and an average clustering accuracy of 88.14\% for all NE classes. |
  - Named Entity Recognition in Manipuri: A Hybrid Approach - based techniques, achieving Recall, Precision, and F-score of 92.26\%, 94.27\%, and 93.3\% respectively. |
  - BiLSTM-CRF Manipuri NER with Character-Level Word Representation - level word representation and word embedding, augmented by a Conditional Random Field (CRF) classifier, achieving an F-Score measure of approximately 98.19\% with RMSprop Gradient Descent (GD) optimizer, and an average clustering accuracy of 88.14\% for all NE classes. |
  - Named Entity Recognition in Manipuri: A Hybrid Approach - based techniques, achieving Recall, Precision, and F-score of 92.26\%, 94.27\%, and 93.3\% respectively. |
  - BiLSTM-CRF Manipuri NER with Character-Level Word Representation - level word representation and word embedding, augmented by a Conditional Random Field (CRF) classifier, achieving an F-Score measure of approximately 98.19\% with RMSprop Gradient Descent (GD) optimizer, and an average clustering accuracy of 88.14\% for all NE classes. |
  - Named Entity Recognition in Manipuri: A Hybrid Approach - based techniques, achieving Recall, Precision, and F-score of 92.26\%, 94.27\%, and 93.3\% respectively. |
  - Named Entity Recognition in Manipuri: A Hybrid Approach - based techniques, achieving Recall, Precision, and F-score of 92.26\%, 94.27\%, and 93.3\% respectively. |
  - BiLSTM-CRF Manipuri NER with Character-Level Word Representation - level word representation and word embedding, augmented by a Conditional Random Field (CRF) classifier, achieving an F-Score measure of approximately 98.19\% with RMSprop Gradient Descent (GD) optimizer, and an average clustering accuracy of 88.14\% for all NE classes. |
  - Named Entity Recognition in Manipuri: A Hybrid Approach - based techniques, achieving Recall, Precision, and F-score of 92.26\%, 94.27\%, and 93.3\% respectively. |
  - BiLSTM-CRF Manipuri NER with Character-Level Word Representation - level word representation and word embedding, augmented by a Conditional Random Field (CRF) classifier, achieving an F-Score measure of approximately 98.19\% with RMSprop Gradient Descent (GD) optimizer, and an average clustering accuracy of 88.14\% for all NE classes. |
  - Named Entity Recognition in Manipuri: A Hybrid Approach - based techniques, achieving Recall, Precision, and F-score of 92.26\%, 94.27\%, and 93.3\% respectively. |
  - BiLSTM-CRF Manipuri NER with Character-Level Word Representation - level word representation and word embedding, augmented by a Conditional Random Field (CRF) classifier, achieving an F-Score measure of approximately 98.19\% with RMSprop Gradient Descent (GD) optimizer, and an average clustering accuracy of 88.14\% for all NE classes. |
  - Named Entity Recognition in Manipuri: A Hybrid Approach - based techniques, achieving Recall, Precision, and F-score of 92.26\%, 94.27\%, and 93.3\% respectively. |
  - BiLSTM-CRF Manipuri NER with Character-Level Word Representation - level word representation and word embedding, augmented by a Conditional Random Field (CRF) classifier, achieving an F-Score measure of approximately 98.19\% with RMSprop Gradient Descent (GD) optimizer, and an average clustering accuracy of 88.14\% for all NE classes. |
  - Named Entity Recognition in Manipuri: A Hybrid Approach - based techniques, achieving Recall, Precision, and F-score of 92.26\%, 94.27\%, and 93.3\% respectively. |
  - BiLSTM-CRF Manipuri NER with Character-Level Word Representation - level word representation and word embedding, augmented by a Conditional Random Field (CRF) classifier, achieving an F-Score measure of approximately 98.19\% with RMSprop Gradient Descent (GD) optimizer, and an average clustering accuracy of 88.14\% for all NE classes. |
  - Named Entity Recognition in Manipuri: A Hybrid Approach - based techniques, achieving Recall, Precision, and F-score of 92.26\%, 94.27\%, and 93.3\% respectively. |
  - BiLSTM-CRF Manipuri NER with Character-Level Word Representation - level word representation and word embedding, augmented by a Conditional Random Field (CRF) classifier, achieving an F-Score measure of approximately 98.19\% with RMSprop Gradient Descent (GD) optimizer, and an average clustering accuracy of 88.14\% for all NE classes. |
  - BiLSTM-CRF Manipuri NER with Character-Level Word Representation - level word representation and word embedding, augmented by a Conditional Random Field (CRF) classifier, achieving an F-Score measure of approximately 98.19\% with RMSprop Gradient Descent (GD) optimizer, and an average clustering accuracy of 88.14\% for all NE classes. |
  - Named Entity Recognition in Manipuri: A Hybrid Approach - based techniques, achieving Recall, Precision, and F-score of 92.26\%, 94.27\%, and 93.3\% respectively. |
  - Named Entity Recognition in Manipuri: A Hybrid Approach - based techniques, achieving Recall, Precision, and F-score of 92.26\%, 94.27\%, and 93.3\% respectively. |
  - BiLSTM-CRF Manipuri NER with Character-Level Word Representation - level word representation and word embedding, augmented by a Conditional Random Field (CRF) classifier, achieving an F-Score measure of approximately 98.19\% with RMSprop Gradient Descent (GD) optimizer, and an average clustering accuracy of 88.14\% for all NE classes. |
  - Named Entity Recognition in Manipuri: A Hybrid Approach - based techniques, achieving Recall, Precision, and F-score of 92.26\%, 94.27\%, and 93.3\% respectively. |
  - BiLSTM-CRF Manipuri NER with Character-Level Word Representation - level word representation and word embedding, augmented by a Conditional Random Field (CRF) classifier, achieving an F-Score measure of approximately 98.19\% with RMSprop Gradient Descent (GD) optimizer, and an average clustering accuracy of 88.14\% for all NE classes. |
  - Named Entity Recognition in Manipuri: A Hybrid Approach - based techniques, achieving Recall, Precision, and F-score of 92.26\%, 94.27\%, and 93.3\% respectively. |
  - BiLSTM-CRF Manipuri NER with Character-Level Word Representation - level word representation and word embedding, augmented by a Conditional Random Field (CRF) classifier, achieving an F-Score measure of approximately 98.19\% with RMSprop Gradient Descent (GD) optimizer, and an average clustering accuracy of 88.14\% for all NE classes. |
  - Named Entity Recognition in Manipuri: A Hybrid Approach - based techniques, achieving Recall, Precision, and F-score of 92.26\%, 94.27\%, and 93.3\% respectively. |
  - BiLSTM-CRF Manipuri NER with Character-Level Word Representation - level word representation and word embedding, augmented by a Conditional Random Field (CRF) classifier, achieving an F-Score measure of approximately 98.19\% with RMSprop Gradient Descent (GD) optimizer, and an average clustering accuracy of 88.14\% for all NE classes. |
  - Named Entity Recognition in Manipuri: A Hybrid Approach - based techniques, achieving Recall, Precision, and F-score of 92.26\%, 94.27\%, and 93.3\% respectively. |
  - BiLSTM-CRF Manipuri NER with Character-Level Word Representation - level word representation and word embedding, augmented by a Conditional Random Field (CRF) classifier, achieving an F-Score measure of approximately 98.19\% with RMSprop Gradient Descent (GD) optimizer, and an average clustering accuracy of 88.14\% for all NE classes. |
  - Named Entity Recognition in Manipuri: A Hybrid Approach - based techniques, achieving Recall, Precision, and F-score of 92.26\%, 94.27\%, and 93.3\% respectively. |
  - BiLSTM-CRF Manipuri NER with Character-Level Word Representation - level word representation and word embedding, augmented by a Conditional Random Field (CRF) classifier, achieving an F-Score measure of approximately 98.19\% with RMSprop Gradient Descent (GD) optimizer, and an average clustering accuracy of 88.14\% for all NE classes. |
  - Named Entity Recognition in Manipuri: A Hybrid Approach - based techniques, achieving Recall, Precision, and F-score of 92.26\%, 94.27\%, and 93.3\% respectively. |
  - BiLSTM-CRF Manipuri NER with Character-Level Word Representation - level word representation and word embedding, augmented by a Conditional Random Field (CRF) classifier, achieving an F-Score measure of approximately 98.19\% with RMSprop Gradient Descent (GD) optimizer, and an average clustering accuracy of 88.14\% for all NE classes. |
  - Named Entity Recognition in Manipuri: A Hybrid Approach - based techniques, achieving Recall, Precision, and F-score of 92.26\%, 94.27\%, and 93.3\% respectively. |
  - BiLSTM-CRF Manipuri NER with Character-Level Word Representation - level word representation and word embedding, augmented by a Conditional Random Field (CRF) classifier, achieving an F-Score measure of approximately 98.19\% with RMSprop Gradient Descent (GD) optimizer, and an average clustering accuracy of 88.14\% for all NE classes. |
  - Named Entity Recognition in Manipuri: A Hybrid Approach - based techniques, achieving Recall, Precision, and F-score of 92.26\%, 94.27\%, and 93.3\% respectively. |
  - BiLSTM-CRF Manipuri NER with Character-Level Word Representation - level word representation and word embedding, augmented by a Conditional Random Field (CRF) classifier, achieving an F-Score measure of approximately 98.19\% with RMSprop Gradient Descent (GD) optimizer, and an average clustering accuracy of 88.14\% for all NE classes. |
  - Named Entity Recognition in Manipuri: A Hybrid Approach - based techniques, achieving Recall, Precision, and F-score of 92.26\%, 94.27\%, and 93.3\% respectively. |
  - BiLSTM-CRF Manipuri NER with Character-Level Word Representation - level word representation and word embedding, augmented by a Conditional Random Field (CRF) classifier, achieving an F-Score measure of approximately 98.19\% with RMSprop Gradient Descent (GD) optimizer, and an average clustering accuracy of 88.14\% for all NE classes. |
  - Named Entity Recognition in Manipuri: A Hybrid Approach - based techniques, achieving Recall, Precision, and F-score of 92.26\%, 94.27\%, and 93.3\% respectively. |
  - BiLSTM-CRF Manipuri NER with Character-Level Word Representation - level word representation and word embedding, augmented by a Conditional Random Field (CRF) classifier, achieving an F-Score measure of approximately 98.19\% with RMSprop Gradient Descent (GD) optimizer, and an average clustering accuracy of 88.14\% for all NE classes. |
  - Named Entity Recognition in Manipuri: A Hybrid Approach - based techniques, achieving Recall, Precision, and F-score of 92.26\%, 94.27\%, and 93.3\% respectively. |
  - BiLSTM-CRF Manipuri NER with Character-Level Word Representation - level word representation and word embedding, augmented by a Conditional Random Field (CRF) classifier, achieving an F-Score measure of approximately 98.19\% with RMSprop Gradient Descent (GD) optimizer, and an average clustering accuracy of 88.14\% for all NE classes. |
  - Named Entity Recognition in Manipuri: A Hybrid Approach - based techniques, achieving Recall, Precision, and F-score of 92.26\%, 94.27\%, and 93.3\% respectively. |
  - BiLSTM-CRF Manipuri NER with Character-Level Word Representation - level word representation and word embedding, augmented by a Conditional Random Field (CRF) classifier, achieving an F-Score measure of approximately 98.19\% with RMSprop Gradient Descent (GD) optimizer, and an average clustering accuracy of 88.14\% for all NE classes. |
  - Named Entity Recognition in Manipuri: A Hybrid Approach - based techniques, achieving Recall, Precision, and F-score of 92.26\%, 94.27\%, and 93.3\% respectively. |
  - BiLSTM-CRF Manipuri NER with Character-Level Word Representation - level word representation and word embedding, augmented by a Conditional Random Field (CRF) classifier, achieving an F-Score measure of approximately 98.19\% with RMSprop Gradient Descent (GD) optimizer, and an average clustering accuracy of 88.14\% for all NE classes. |
  - Named Entity Recognition in Manipuri: A Hybrid Approach - based techniques, achieving Recall, Precision, and F-score of 92.26\%, 94.27\%, and 93.3\% respectively. |
  - BiLSTM-CRF Manipuri NER with Character-Level Word Representation - level word representation and word embedding, augmented by a Conditional Random Field (CRF) classifier, achieving an F-Score measure of approximately 98.19\% with RMSprop Gradient Descent (GD) optimizer, and an average clustering accuracy of 88.14\% for all NE classes. |
  - Named Entity Recognition for Manipuri Using Support Vector Machine - Score of 94.59\%. |
  - Named Entity Recognition in Manipuri: A Hybrid Approach - based techniques, achieving Recall, Precision, and F-score of 92.26\%, 94.27\%, and 93.3\% respectively. |
  - BiLSTM-CRF Manipuri NER with Character-Level Word Representation - level word representation and word embedding, augmented by a Conditional Random Field (CRF) classifier, achieving an F-Score measure of approximately 98.19\% with RMSprop Gradient Descent (GD) optimizer, and an average clustering accuracy of 88.14\% for all NE classes. |
  - Named Entity Recognition in Manipuri: A Hybrid Approach - based techniques, achieving Recall, Precision, and F-score of 92.26\%, 94.27\%, and 93.3\% respectively. |
  - BiLSTM-CRF Manipuri NER with Character-Level Word Representation - level word representation and word embedding, augmented by a Conditional Random Field (CRF) classifier, achieving an F-Score measure of approximately 98.19\% with RMSprop Gradient Descent (GD) optimizer, and an average clustering accuracy of 88.14\% for all NE classes. |
  - Web Based Manipuri Corpus for Multiword NER and Reduplicated MWEs Identification using SVM - based Manipuri corpus for identifying reduplicated multiword expressions (MWE) and multiword named entities (NE) using a Support Vector Machine (SVM) learning technique, achieving recall, precision, and F-score values of 94.62\%, 93.53\%, and 94.07\% respectively for reduplicated MWEs, and 94.82\%, 93.12\%, and 93.96\% respectively for multiword NE. |
  - CRF based Name Entity Recognition (NER) in Manipuri: A highly agglutinative Indian Language - Score of 83.33\%. |
  - Deep Neural Model for Manipuri Multiword Named Entity Recognition with Unsupervised Cluster Feature - Word Named Entities (MNEs) in Manipuri using a Long Short Term Memory (LSTM) recurrent neural network model augmented with Part Of Speech (POS) embeddings and word cluster information obtained through K-means clustering, demonstrating performance comparison with other machine learning-based models. |
  - BiLSTM-CRF Manipuri NER with Character-Level Word Representation - level word representation and word embedding, augmented by a Conditional Random Field (CRF) classifier, achieving an F-Score measure of approximately 98.19\% with RMSprop Gradient Descent (GD) optimizer, and an average clustering accuracy of 88.14\% for all NE classes. |
  - BiLSTM-CRF Manipuri NER with Character-Level Word Representation - level word representation and word embedding, augmented by a Conditional Random Field (CRF) classifier, achieving an F-Score measure of approximately 98.19\% with RMSprop Gradient Descent (GD) optimizer, and an average clustering accuracy of 88.14\% for all NE classes. |
  - BiLSTM-CRF Manipuri NER with Character-Level Word Representation - level word representation and word embedding, augmented by a Conditional Random Field (CRF) classifier, achieving an F-Score measure of approximately 98.19\% with RMSprop Gradient Descent (GD) optimizer, and an average clustering accuracy of 88.14\% for all NE classes. |
  - Named Entity Recognition in Manipuri: A Hybrid Approach - based techniques, achieving Recall, Precision, and F-score of 92.26\%, 94.27\%, and 93.3\% respectively. |
  - Named Entity Recognition in Manipuri: A Hybrid Approach - based techniques, achieving Recall, Precision, and F-score of 92.26\%, 94.27\%, and 93.3\% respectively. |
  - BiLSTM-CRF Manipuri NER with Character-Level Word Representation - level word representation and word embedding, augmented by a Conditional Random Field (CRF) classifier, achieving an F-Score measure of approximately 98.19\% with RMSprop Gradient Descent (GD) optimizer, and an average clustering accuracy of 88.14\% for all NE classes. |
  - Named Entity Recognition in Manipuri: A Hybrid Approach - based techniques, achieving Recall, Precision, and F-score of 92.26\%, 94.27\%, and 93.3\% respectively. |
  - BiLSTM-CRF Manipuri NER with Character-Level Word Representation - level word representation and word embedding, augmented by a Conditional Random Field (CRF) classifier, achieving an F-Score measure of approximately 98.19\% with RMSprop Gradient Descent (GD) optimizer, and an average clustering accuracy of 88.14\% for all NE classes. |
  - Named Entity Recognition in Manipuri: A Hybrid Approach - based techniques, achieving Recall, Precision, and F-score of 92.26\%, 94.27\%, and 93.3\% respectively. |
  - BiLSTM-CRF Manipuri NER with Character-Level Word Representation - level word representation and word embedding, augmented by a Conditional Random Field (CRF) classifier, achieving an F-Score measure of approximately 98.19\% with RMSprop Gradient Descent (GD) optimizer, and an average clustering accuracy of 88.14\% for all NE classes. |
  - Named Entity Recognition in Manipuri: A Hybrid Approach - based techniques, achieving Recall, Precision, and F-score of 92.26\%, 94.27\%, and 93.3\% respectively. |
  - BiLSTM-CRF Manipuri NER with Character-Level Word Representation - level word representation and word embedding, augmented by a Conditional Random Field (CRF) classifier, achieving an F-Score measure of approximately 98.19\% with RMSprop Gradient Descent (GD) optimizer, and an average clustering accuracy of 88.14\% for all NE classes. |
  - Named Entity Recognition in Manipuri: A Hybrid Approach - based techniques, achieving Recall, Precision, and F-score of 92.26\%, 94.27\%, and 93.3\% respectively. |
  - BiLSTM-CRF Manipuri NER with Character-Level Word Representation - level word representation and word embedding, augmented by a Conditional Random Field (CRF) classifier, achieving an F-Score measure of approximately 98.19\% with RMSprop Gradient Descent (GD) optimizer, and an average clustering accuracy of 88.14\% for all NE classes. |
  - Named Entity Recognition in Manipuri: A Hybrid Approach - based techniques, achieving Recall, Precision, and F-score of 92.26\%, 94.27\%, and 93.3\% respectively. |
  - BiLSTM-CRF Manipuri NER with Character-Level Word Representation - level word representation and word embedding, augmented by a Conditional Random Field (CRF) classifier, achieving an F-Score measure of approximately 98.19\% with RMSprop Gradient Descent (GD) optimizer, and an average clustering accuracy of 88.14\% for all NE classes. |
  - Named Entity Recognition in Manipuri: A Hybrid Approach - based techniques, achieving Recall, Precision, and F-score of 92.26\%, 94.27\%, and 93.3\% respectively. |
  - BiLSTM-CRF Manipuri NER with Character-Level Word Representation - level word representation and word embedding, augmented by a Conditional Random Field (CRF) classifier, achieving an F-Score measure of approximately 98.19\% with RMSprop Gradient Descent (GD) optimizer, and an average clustering accuracy of 88.14\% for all NE classes. |
  - Named Entity Recognition in Manipuri: A Hybrid Approach - based techniques, achieving Recall, Precision, and F-score of 92.26\%, 94.27\%, and 93.3\% respectively. |
  - BiLSTM-CRF Manipuri NER with Character-Level Word Representation - level word representation and word embedding, augmented by a Conditional Random Field (CRF) classifier, achieving an F-Score measure of approximately 98.19\% with RMSprop Gradient Descent (GD) optimizer, and an average clustering accuracy of 88.14\% for all NE classes. |
  - Named Entity Recognition in Manipuri: A Hybrid Approach - based techniques, achieving Recall, Precision, and F-score of 92.26\%, 94.27\%, and 93.3\% respectively. |
  - BiLSTM-CRF Manipuri NER with Character-Level Word Representation - level word representation and word embedding, augmented by a Conditional Random Field (CRF) classifier, achieving an F-Score measure of approximately 98.19\% with RMSprop Gradient Descent (GD) optimizer, and an average clustering accuracy of 88.14\% for all NE classes. |
  - Named Entity Recognition in Manipuri: A Hybrid Approach - based techniques, achieving Recall, Precision, and F-score of 92.26\%, 94.27\%, and 93.3\% respectively. |
  - BiLSTM-CRF Manipuri NER with Character-Level Word Representation - level word representation and word embedding, augmented by a Conditional Random Field (CRF) classifier, achieving an F-Score measure of approximately 98.19\% with RMSprop Gradient Descent (GD) optimizer, and an average clustering accuracy of 88.14\% for all NE classes. |
  - Named Entity Recognition in Manipuri: A Hybrid Approach - based techniques, achieving Recall, Precision, and F-score of 92.26\%, 94.27\%, and 93.3\% respectively. |
  - Named Entity Recognition in Manipuri: A Hybrid Approach - based techniques, achieving Recall, Precision, and F-score of 92.26\%, 94.27\%, and 93.3\% respectively. |
  - BiLSTM-CRF Manipuri NER with Character-Level Word Representation - level word representation and word embedding, augmented by a Conditional Random Field (CRF) classifier, achieving an F-Score measure of approximately 98.19\% with RMSprop Gradient Descent (GD) optimizer, and an average clustering accuracy of 88.14\% for all NE classes. |
  - BiLSTM-CRF Manipuri NER with Character-Level Word Representation - level word representation and word embedding, augmented by a Conditional Random Field (CRF) classifier, achieving an F-Score measure of approximately 98.19\% with RMSprop Gradient Descent (GD) optimizer, and an average clustering accuracy of 88.14\% for all NE classes. |
  - Named Entity Recognition in Manipuri: A Hybrid Approach - based techniques, achieving Recall, Precision, and F-score of 92.26\%, 94.27\%, and 93.3\% respectively. |
  - BiLSTM-CRF Manipuri NER with Character-Level Word Representation - level word representation and word embedding, augmented by a Conditional Random Field (CRF) classifier, achieving an F-Score measure of approximately 98.19\% with RMSprop Gradient Descent (GD) optimizer, and an average clustering accuracy of 88.14\% for all NE classes. |
  - Named Entity Recognition in Manipuri: A Hybrid Approach - based techniques, achieving Recall, Precision, and F-score of 92.26\%, 94.27\%, and 93.3\% respectively. |
  - BiLSTM-CRF Manipuri NER with Character-Level Word Representation - level word representation and word embedding, augmented by a Conditional Random Field (CRF) classifier, achieving an F-Score measure of approximately 98.19\% with RMSprop Gradient Descent (GD) optimizer, and an average clustering accuracy of 88.14\% for all NE classes. |
  - Named Entity Recognition in Manipuri: A Hybrid Approach - based techniques, achieving Recall, Precision, and F-score of 92.26\%, 94.27\%, and 93.3\% respectively. |
  - Named Entity Recognition in Manipuri: A Hybrid Approach - based techniques, achieving Recall, Precision, and F-score of 92.26\%, 94.27\%, and 93.3\% respectively. |
  - BiLSTM-CRF Manipuri NER with Character-Level Word Representation - level word representation and word embedding, augmented by a Conditional Random Field (CRF) classifier, achieving an F-Score measure of approximately 98.19\% with RMSprop Gradient Descent (GD) optimizer, and an average clustering accuracy of 88.14\% for all NE classes. |
  - Named Entity Recognition in Manipuri: A Hybrid Approach - based techniques, achieving Recall, Precision, and F-score of 92.26\%, 94.27\%, and 93.3\% respectively. |
  - BiLSTM-CRF Manipuri NER with Character-Level Word Representation - level word representation and word embedding, augmented by a Conditional Random Field (CRF) classifier, achieving an F-Score measure of approximately 98.19\% with RMSprop Gradient Descent (GD) optimizer, and an average clustering accuracy of 88.14\% for all NE classes. |
  - Named Entity Recognition in Manipuri: A Hybrid Approach - based techniques, achieving Recall, Precision, and F-score of 92.26\%, 94.27\%, and 93.3\% respectively. |
  - BiLSTM-CRF Manipuri NER with Character-Level Word Representation - level word representation and word embedding, augmented by a Conditional Random Field (CRF) classifier, achieving an F-Score measure of approximately 98.19\% with RMSprop Gradient Descent (GD) optimizer, and an average clustering accuracy of 88.14\% for all NE classes. |
  - Named Entity Recognition in Manipuri: A Hybrid Approach - based techniques, achieving Recall, Precision, and F-score of 92.26\%, 94.27\%, and 93.3\% respectively. |
  - BiLSTM-CRF Manipuri NER with Character-Level Word Representation - level word representation and word embedding, augmented by a Conditional Random Field (CRF) classifier, achieving an F-Score measure of approximately 98.19\% with RMSprop Gradient Descent (GD) optimizer, and an average clustering accuracy of 88.14\% for all NE classes. |
- Morphological Analysis
  - Morphological Analyzer for Manipuri: Design and Implementation
  - Morphological Analyzer for Manipuri: Design and Implementation
  - Morphological Analyzer for Manipuri: Design and Implementation
  - Morphological Analyzer for Manipuri: Design and Implementation
  - Morphological Analyzer for Manipuri: Design and Implementation
  - Morphological Analyzer for Manipuri: Design and Implementation
  - Morphological Analyzer for Manipuri: Design and Implementation
  - Morphological Analyzer for Manipuri: Design and Implementation
  - Morphological Analyzer for Manipuri: Design and Implementation
  - Morphological Analyzer for Manipuri: Design and Implementation
  - Morphological Analyzer for Manipuri: Design and Implementation
  - Morphological Analyzer for Manipuri: Design and Implementation
  - Morphological Analyzer for Manipuri: Design and Implementation
  - Morphotactics of Manipuri Adjectives: A FiniteState Approach - state model to represent the morphotactic rule of Manipuri adjective word forms, which are derived from verb roots using specific affixes, with rules composed to describe their simple agglutinative morphology and more complex structures, resulting in a system capable of analyzing and recognizing adjectives through finite-state networks, utilizing a root lexicon and an affix dictionary. |
  - Morphological Analyzer for Manipuri: Design and Implementation
  - Morphological Analyzer for Manipuri: Design and Implementation
  - Morphological Analyzer for Manipuri: Design and Implementation
  - Morphological Analyzer for Manipuri: Design and Implementation
  - Morphological Analyzer for Manipuri: Design and Implementation
  - Morphological Analyzer for Manipuri: Design and Implementation
  - Morphological Analyzer for Manipuri: Design and Implementation
  - Morphological Analyzer for Manipuri: Design and Implementation
  - Morphological Analyzer for Manipuri: Design and Implementation
  - Morphological Analyzer for Manipuri: Design and Implementation
  - Morphological Analyzer for Manipuri: Design and Implementation
  - Morphological Analyzer for Manipuri: Design and Implementation
  - Morphological Analyzer for Manipuri: Design and Implementation
  - Morphological Analyzer for Manipuri: Design and Implementation
  - Morphological Analyzer for Manipuri: Design and Implementation
  - Morphological Analyzer for Manipuri: Design and Implementation
  - Morphological Analyzer for Manipuri: Design and Implementation
  - Morphological Analyzer for Manipuri: Design and Implementation
  - Morphological Analyzer for Manipuri: Design and Implementation
  - Morphological Analyzer for Manipuri: Design and Implementation
  - Morphological Analyzer for Manipuri: Design and Implementation
  - Morphological Analyzer for Manipuri: Design and Implementation
  - Morphological Analyzer for Manipuri: Design and Implementation
  - Manipuri Morphological Analyzer - English dictionary for identifying word morphemes and an affix dictionary for categorizing affix types.
  - Word Class and Sentence Type Identification in Manipuri Morophological Analyzer - English dictionary for root words and an affix dictionary for affix types, yields surface-level word analysis aiding in the development of a Manipuri-English machine translation system, showcasing promising results. |
  - Manipuri Morpheme Identification - gram analysis with Standard Deviation technique for morpheme identification, achieving recall of 59.80%, precision of 83.02%, and an f-score of 69.52%. |
  - Morphological Analysis for Manipuri Nominal Category Words with Finite State Techniques - deterministic finite automata to deterministic finite automata, facilitating morphological analysis without a lexicon. |
  - Morphotactics of Manipuri Adjectives: A FiniteState Approach - state model to represent the morphotactic rule of Manipuri adjective word forms, which are derived from verb roots using specific affixes, with rules composed to describe their simple agglutinative morphology and more complex structures, resulting in a system capable of analyzing and recognizing adjectives through finite-state networks, utilizing a root lexicon and an affix dictionary. |
  - Manipuri morphological generator
  - Morphological Analysis of Manipuri Language
  - Morphotactics of Manipuri Verbs: A Finite State Approach
  - Manipuri Morphological Analysis
  - Allomorphs in Meeteilon (Manipuri) Morphology
  - Morphological Analyzer for Manipuri: Design and Implementation
  - Morphological Analyzer for Manipuri: Design and Implementation
  - Morphological Analyzer for Manipuri: Design and Implementation
  - Morphological Analyzer for Manipuri: Design and Implementation
  - Morphological Analyzer for Manipuri: Design and Implementation
  - Morphological Analyzer for Manipuri: Design and Implementation
  - Morphological Analyzer for Manipuri: Design and Implementation
  - Morphological Analyzer for Manipuri: Design and Implementation
  - Morphological Analyzer for Manipuri: Design and Implementation
  - Morphological Analyzer for Manipuri: Design and Implementation
  - Morphological Analyzer for Manipuri: Design and Implementation
  - Morphological Analyzer for Manipuri: Design and Implementation
  - Morphological Analyzer for Manipuri: Design and Implementation
  - Morphological Analyzer for Manipuri: Design and Implementation
- Syllabification, Stemming, Chunking
  - Automatic Segmentation of Manipuri (Meiteilon) Word into Syllabic Units - Score of 82.18. |
  - An HMM based semi-automatic syllable labeling system for Manipuri language - Automatic Syllable Labeling System for Manipuri, utilizing HMM toolkit (HTK) and WaveSurfer, achieving an average deviation of 25 ms and employing detection rates based on time deviations for syllable segmentation. |
  - Automatic Syllabification for Manipuri language - driven method for automatic syllabification by employing entropy-based phonotactic segmentation, sequence labeling approaches, and a hybrid method, achieving up to 98\% word accuracy.|
  - Automatic Syllabification Rules for Manipuri Language - to-speech conversion and speech recognition. |
  - Chunking in Manipuri Using CRF - measure of 74.21\%. |
  - Manipuri Chunking: An Incremental Model with POS and RMWE - measure of 77.50\% |
  - Development of a Manipuri stemmer: A hybrid approach
- Word Sense Disambiguation
  - Word Sense Disambiguation - based features to predict the senses of polysemous words with an accuracy of 71.75\%. |

ecosyste.ms

Data

Tools

Indexes

Applications

Experiments

Awesome

Manipuri-NLP

RMWE

Sentiment Analysis

Speech Technologies

Word Sense Disambiguation

Corpus Creation and E-Dictionary

Parsing

Machine Translation

Transliteration

Index

POS Tagging

Named Entity Recognition

Morphological Analysis

Syllabification, Stemming, Chunking

Word Sense Disambiguation