https://github.com/codename-detective/neural-machine-translation
This GitHub repository houses an innovative implementation of Neural Machine Translation (NMT) using state-of-the-art sequence-to-sequence networks. The primary focus is on enhancing translation quality through progressively advanced architectural improvements.
https://github.com/codename-detective/neural-machine-translation
attention-mechanism deep-learning encoder-decoder-architecture natural-language-processing natural-language-translation
Last synced: about 1 month ago
JSON representation
This GitHub repository houses an innovative implementation of Neural Machine Translation (NMT) using state-of-the-art sequence-to-sequence networks. The primary focus is on enhancing translation quality through progressively advanced architectural improvements.
- Host: GitHub
- URL: https://github.com/codename-detective/neural-machine-translation
- Owner: CodeName-Detective
- Created: 2023-08-08T22:03:45.000Z (almost 3 years ago)
- Default Branch: main
- Last Pushed: 2023-08-10T16:38:21.000Z (almost 3 years ago)
- Last Synced: 2025-03-05T07:46:51.569Z (over 1 year ago)
- Topics: attention-mechanism, deep-learning, encoder-decoder-architecture, natural-language-processing, natural-language-translation
- Language: Jupyter Notebook
- Homepage:
- Size: 2.97 MB
- Stars: 0
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# Neural-Machine-Translation
1. Constructed and deployed a Sequence-to-Sequence network using an encoding and decoding paradigm, utilizing LSTM nodes as the foundation. Implementation achieved a noteworthy test Bleu score of 0.365.
2. Executed a bidirectional Sequence-to-Sequence network, incorporating both forward and backward encoding. Implementation, succeeded in a commendable test Bleu score of 0.369, highlighting the model’s proficiency in generating high-quality sequences.
3. Performed a Sequence-to-Sequence network with bidirectional encoding and incorporated an Attention mechanism in the decoding process. This advanced architecture led to remarkable results, attaining a notable test Bleu score of 0.406. The model’s ability to generate accurate and coherent sequences was improved by the inclusion of Attention.