https://github.com/miftahurrrizki/custom-named-entity-recognition-with-bilstm-crf-and-spacy

https://github.com/miftahurrrizki/custom-named-entity-recognition-with-bilstm-crf-and-spacy

bilstm-crf-model bilstm-model crf-model indonesia named-entity-recognition nervaluate nlp-keywords-extraction seqeval spacy

Last synced: 6 days ago
JSON representation

• Host: GitHub
• URL: https://github.com/miftahurrrizki/custom-named-entity-recognition-with-bilstm-crf-and-spacy
• Owner: miftahurrrizki
• Created: 2024-08-26T08:46:51.000Z (2 months ago)
• Default Branch: main
• Last Pushed: 2024-09-02T03:33:04.000Z (2 months ago)
• Last Synced: 2024-10-31T04:05:58.555Z (6 days ago)
• Topics: bilstm-crf-model, bilstm-model, crf-model, indonesia, named-entity-recognition, nervaluate, nlp-keywords-extraction, seqeval, spacy
• Language: Jupyter Notebook
• Homepage:
• Size: 284 KB
• Stars: 1
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        
# Named Entity Recognition using BiLSTM-CRF and Spacy

This project implements a Bidirectional LSTM with Conditional Random Fields (BiLSTM-CRF) and Spacy for Named Entity Recognition (NER) tasks. The model is designed to identify and classify named entities in text, such as locations and seaweed species.

------------------

![image](https://github.com/user-attachments/assets/b0f364d4-745b-4f4b-a8dd-23da59596187)

Model Architecture (BiLSTM-CRF)

------------------

![image](https://github.com/user-attachments/assets/b38ede97-42d3-4716-a471-2e7f0d4f062c)

Model Accuracy for each entity

------------------

## Requirements

- Python 3.7+

- TensorFlow 1.15.0

- Keras 2.2.4

- keras-contrib (for CRF layer)

You can install the required packages using:

```bash

pip install tensorflow==1.15.0 keras==2.2.4

pip install git+https://www.github.com/keras-team/keras-contrib.git