HW-TSC’s Participation in the WMT 2020 News Translation Shared Task

Daimeng Wei, Hengchao Shang, Zhanglin Wu, Zhengzhe Yu, Liangyou Li, Jiaxin Guo, Minghan Wang, Hao Yang, Lizhi Lei, Ying Qin, Shiliang Sun


Abstract
This paper presents our work in the WMT 2020 News Translation Shared Task. We participate in 3 language pairs including Zh/En, Km/En, and Ps/En and in both directions under the constrained condition. We use the standard Transformer-Big model as the baseline and obtain the best performance via two variants with larger parameter sizes. We perform detailed pre-processing and filtering on the provided large-scale bilingual and monolingual dataset. Several commonly used strategies are used to train our models such as Back Translation, Ensemble Knowledge Distillation, etc. We also conduct experiment with similar language augmentation, which lead to positive results, although not used in our submission. Our submission obtains remarkable results in the final evaluation.
Anthology ID:
2020.wmt-1.31
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:
293–299
Language:
URL:
https://aclanthology.org/2020.wmt-1.31
DOI:
Bibkey:
Cite (ACL):
Daimeng Wei, Hengchao Shang, Zhanglin Wu, Zhengzhe Yu, Liangyou Li, Jiaxin Guo, Minghan Wang, Hao Yang, Lizhi Lei, Ying Qin, and Shiliang Sun. 2020. HW-TSC’s Participation in the WMT 2020 News Translation Shared Task. In Proceedings of the Fifth Conference on Machine Translation, pages 293–299, Online. Association for Computational Linguistics.
Cite (Informal):
HW-TSC’s Participation in the WMT 2020 News Translation Shared Task (Wei et al., WMT 2020)
Copy Citation:
PDF:
https://preview.aclanthology.org/author-url/2020.wmt-1.31.pdf
Video:
 https://slideslive.com/38939573