Tencent neural machine translation systems for wmt18

Abstract
We participated in the WMT 2018 shared news translation task on English-Chinese language pair. Our systems are based on attentional sequence-to-sequence models with some form of recursion and self-attention. Some data augmentation methods are also introduced to improve the translation performance. The best translation result is obtained with ensemble and reranking techniques. Our Chinese→ English system achieved the highest cased BLEU score among all 16 submitted systems, and our English-Chinese system ranked the third out of 18 submitted systems.

Please cite as:

@inproceedings{wang2018tencent,
  title={Tencent neural machine translation systems for wmt18},
  author={Wang, Mingxuan and Gong, Li and Zhu, Wenhuan and Xie, Jun and Bian, Chao},
  booktitle={Proceedings of the Third Conference on Machine Translation: Shared Task Papers},
  pages={522--527},
  year={2018}
}