Tencent Neural Machine Translation Systems for WMT18

Mingxuan Wang, Li Gong, Wenhuan Zhu, Jun Xie, Chao Bian


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.
Anthology ID:
W18-6429
Volume:
Proceedings of the Third Conference on Machine Translation: Shared Task Papers
Month:
October
Year:
2018
Address:
Belgium, Brussels
Venues:
EMNLP | WMT | WS
SIG:
SIGMT
Publisher:
Association for Computational Linguistics
Note:
Pages:
522–527
Language:
URL:
https://aclanthology.org/W18-6429
DOI:
10.18653/v1/W18-6429
Bibkey:
Cite (ACL):
Mingxuan Wang, Li Gong, Wenhuan Zhu, Jun Xie, and Chao Bian. 2018. Tencent Neural Machine Translation Systems for WMT18. In Proceedings of the Third Conference on Machine Translation: Shared Task Papers, pages 522–527, Belgium, Brussels. Association for Computational Linguistics.
Cite (Informal):
Tencent Neural Machine Translation Systems for WMT18 (Wang et al., 2018)
Copy Citation:
PDF:
https://aclanthology.org/W18-6429.pdf