/Seq2seq-with-attention

Basic Neural Machine Translation (NMT) using a Sequence-to-Sequence Network with attention mechanism. (in PyTorch)

Primary LanguagePython

NMT by Jointly Learning to Algin and Translate (Using Seq2seq + Attention)

Sequence to sequence networks are powerful methods to use two recurrent neural networks (encoder-decoder) to turn one sequence into another; in this case, a French-English translation.

This code uses modified parts of the tutorial given by PyTorch tutorials in "Translation with a Sequence to Sequence Network and Attention" in the following link:

https://pytorch.org/tutorials/intermediate/seq2seq_translation_tutorial.html

The Seq2seq model architecture used in this project closely follows the above tutorial.

References

For further studies about word embeddings, read the papers below:

  1. NMT by Jointly Learning to Algin and Translate (Bahdanau et al.)
  2. Sequence to Sequence Learning with Neural Networks (Sutskever et al.)

Run

python3 train.py