HW-TSC’s Participation in the WMT 2021 Triangular MT Shared Task

Zongyao Li, Daimeng Wei, Hengchao Shang, Xiaoyu Chen, Zhanglin Wu, Zhengzhe Yu, Jiaxin Guo, Minghan Wang, Lizhi Lei, Min Zhang, Hao Yang, Ying Qin


Abstract
This paper presents the submission of Huawei Translation Service Center (HW-TSC) to WMT 2021 Triangular MT Shared Task. We participate in the Russian-to-Chinese task under the constrained condition. We use Transformer architecture and obtain the best performance via a variant with larger parameter sizes. We perform detailed data pre-processing and filtering on the provided large-scale bilingual data. Several strategies are used to train our models, such as Multilingual Translation, Back Translation, Forward Translation, Data Denoising, Average Checkpoint, Ensemble, Fine-tuning, etc. Our system obtains 32.5 BLEU on the dev set and 27.7 BLEU on the test set, the highest score among all submissions.
Anthology ID:
2021.wmt-1.37
Volume:
Proceedings of the Sixth Conference on Machine Translation
Month:
November
Year:
2021
Address:
Online
Venues:
EMNLP | WMT
SIG:
SIGMT
Publisher:
Association for Computational Linguistics
Note:
Pages:
325–330
Language:
URL:
https://aclanthology.org/2021.wmt-1.37
DOI:
Bibkey:
Cite (ACL):
Zongyao Li, Daimeng Wei, Hengchao Shang, Xiaoyu Chen, Zhanglin Wu, Zhengzhe Yu, Jiaxin Guo, Minghan Wang, Lizhi Lei, Min Zhang, Hao Yang, and Ying Qin. 2021. HW-TSC’s Participation in the WMT 2021 Triangular MT Shared Task. In Proceedings of the Sixth Conference on Machine Translation, pages 325–330, Online. Association for Computational Linguistics.
Cite (Informal):
HW-TSC’s Participation in the WMT 2021 Triangular MT Shared Task (Li et al., WMT 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.wmt-1.37.pdf