For nlp final project

• gru_no_attention.ipynb: Seq2Seq model with GRU RNN model without attention
• bidirection_gru.ipynb: bidirectional GRU RNN model with luong attention
• bidirection_lstm.ipynb: bidirectional LSTM RNN model with luong attention, evaluation, beam search evaluation, dataloader
• cnn.ipynb: Seq2Seq model with CNN encoder
• self_attention.ipynb: self attention
• Archive: historical codes

• Tianyi Bi
• Yiyan Chen
• Manwen Li
• Tinghao Li

• https://stackoverflow.com/questions/50571991/implementing-luong-attention-in-pytorch
• https://pytorch.org/tutorials/intermediate/seq2seq_translation_tutorial.html
• http://nlp.seas.harvard.edu/2018/04/03/attention.html