Seq2Seq Translation

Implement By Bidirectional GRU And Transformer In Pytorch

Before You Run The Code

You should download the data through the link below.

https://pan.baidu.com/s/1ptpghzFEAQIS4A_5EDF_0g
Retrieve Code is 1916.

Then put them in the right place. Just like

seq2seq_translation/seq2seq_translation_gru/data/chs-eng-cut.txt

seq2seq_translation/seq2seq_translation_transformer/data/train.txt

Run the train.py to start training.

If you want to use your own dataset, just replace the file you download and make it same format as mine.

(for each line in data file “src + ‘\t’ + trg”)

At last, thanks to the public dataset this project based on, news-commentary-v14, wikititles-v1 and translation2019zh-train.

GitHub

View Github