This is the official codebase for the following papers, implemented in tensorflow:
(1) Long Zhou, Jiajun Zhang, Chengqing Zong. Synchronous Bidirectional Nueral Machine Translaiton. In Transactions of ACL 2019. [PDF]
(2) Jiajun Zhang, Long Zhou, Yang Zhao, Chengqing Zong. Synchronous Bidirectional Inference for Neural Sequence Generation. arXiv preprint arXiv:1902.08955.
- 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},
}
@article{Zhang:2019:Arxiv,
author = {Zhang, Jiajun and Zhou, Long and Zhao, Yang and Zong, Chengqing},
title = {Synchronous Bidirectional Inference for Neural Sequence Generation},
journal = {arXiv preprint arXiv:1902.08955},
year = {2019},
}
If you have questions, suggestions and bug reports, please email long.zhou@nlpr.ia.ac.cn or jjzhang@nlpr.ia.ac.cn.