This is the official codebase for the following paper, implemented in tensorflow:
Long Zhou, Jiajun Zhang, Chengqing Zong. Synchronous Bidirectional Nueral Machine Translaiton. In Transactions of ACL 2019. [PDF]
- python2.7
- tensorflow-gpu >=1.4
- cuda >=8.0
- Preprocessing. construct pseudo training data using Transformer as introduced in the paper,
and then run
./datagen.sh
. - Training. run
./train.sh
. - Inference. run
./test.sh
.
If you found this code useful in your research, please cite:
@article{Zhou:2019:TACL,
author = {Zhou, Long and Zhang, Jiajun and Zong, Chengqing},
title = {Synchronous Bidirectional Nueral Machine Translaiton},
journal = {Transactions of the Association for Computational Linguistics},
year = {2019},
}
If you have questions, suggestions and bug reports, please email wszlong@gmail.com or long.zhou@nlpr.ia.ac.cn.