Skip to content

Implement en-fr translation task by implenting seq2seq, encoder-decoder in RNN layers with Attention mechanism and Beamsearch inference decoder in TensorFlow 1.3

Notifications You must be signed in to change notification settings

chen372/TensorFlow-Seq2Seq

 
 

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

20 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

TensorFlow-Seq2Seq

Implement English-to-French Neural Machine Translation task by implenting seq2seq in TensorFlow 1.3.

Datasets

Shared Task: Machine Translation of News, WMT 16

I took the English and French dataset in news-test2013 as training example.
The hyperparameter and other details in codes are not yet tuned.

Requirements

  • Python 3.5
  • TensorFlow 1.3
  • NLTK

Features

  • Tokenization
  • Padding (EOS in the end of encoder input; GO in the beginning of decoder input and EOS in the end)
  • Vocabulary list building
  • Autoencoder/encoder-decoder in multi-RNN-layers
  • Attention mechanism (Luong's)
  • Batch-training process
  • Beamsearch/basic inference decoder

Features In Progress

  • Bidirectional encoder
  • BLEU score metrics
  • Bucketing (Optional. Because TensorFlow's dynamic_decode doesn't require fixed length input anymore)

Usage

Import mySeq2Seq.py to have Seq2SeqModel class.
You may refer to train.ipynb for the training process and data flow.

Reference

Massive Exploration of Neural Machine Translation Architectures
TensorFlow / nmt
JayParks / tf-seq2seq

About

Implement en-fr translation task by implenting seq2seq, encoder-decoder in RNN layers with Attention mechanism and Beamsearch inference decoder in TensorFlow 1.3

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • Jupyter Notebook 81.3%
  • Python 18.7%