This project is a simple implementation of Tensor2tensor (https://github.com/tensorflow/tensor2tensor) for machine translation.
Preprosessing. Prepare the parallel data (token, bpe, vocab, and so on), run ./datagen.sh to generate data.
Training. Modify the model params (transformer_params_big or transformer_params_base, basic params are set in models/common_hparms.py), and run ./train.sh.
inference. Run the command to translate source sentence: ./test.sh.
Once you have trained the model, you can also use a C++/CUDA Transformer-translator to translate source language.
If you have questions, suggestions and bug reports, please email wszlong@gmail.com or long.zhou@nlpr.ia.ac.cn.