Tencent Neural Machine Translation Systems for the WMT20 News Translation Task

Shuangzhi Wu, Xing Wang, Longyue Wang, Fangxu Liu, Jun Xie, Zhaopeng Tu, Shuming Shi, Mu Li


Abstract
This paper describes Tencent Neural Machine Translation systems for the WMT 2020 news translation tasks. We participate in the shared news translation task on English Chinese and English German language pairs. Our systems are built on deep Transformer and several data augmentation methods. We propose a boosted in-domain finetuning method to improve single models. Ensemble is used to combine single models and we propose an iterative transductive ensemble method which can further improve the translation performance based on the ensemble results. We achieve a BLEU score of 36.8 and the highest chrF score of 0.648 on Chinese English task.
Anthology ID:
2020.wmt-1.34
Volume:
Proceedings of the Fifth Conference on Machine Translation
Month:
November
Year:
2020
Address:
Online
Venue:
WMT
SIG:
SIGMT
Publisher:
Association for Computational Linguistics
Note:
Pages:
313–319
Language:
URL:
https://aclanthology.org/2020.wmt-1.34
DOI:
Bibkey:
Cite (ACL):
Shuangzhi Wu, Xing Wang, Longyue Wang, Fangxu Liu, Jun Xie, Zhaopeng Tu, Shuming Shi, and Mu Li. 2020. Tencent Neural Machine Translation Systems for the WMT20 News Translation Task. In Proceedings of the Fifth Conference on Machine Translation, pages 313–319, Online. Association for Computational Linguistics.
Cite (Informal):
Tencent Neural Machine Translation Systems for the WMT20 News Translation Task (Wu et al., WMT 2020)
Copy Citation:
PDF:
https://preview.aclanthology.org/ingestion-script-update/2020.wmt-1.34.pdf