seq2seq

Sequence to sequence network implementation in Pytorch

1. simple_seq2seq.py: This code contains the implementation of paper Sequence to Sequence Learning with Neural Networks
2. phrase_seq2seq.py: This code contains the implementation of paper Learning Phrase Representations using RNN Encoder–Decoder for Statistical Machine Translation
3. attention_seq2seq.py: This code contains the implementation of paper Neural Machine translation by Jointly Learning to Align and Translate
4. padded_seq2seq.py: This code contains the usage of padded sequences and masking
5. transformer.py: This code contains the implementation of paper Attention is All You Need
6. BERT_basic.py: This code contains the implementation of paper BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding