The Volctrans GLAT System: Non-autoregressive Translation Meets WMT21
Lihua Qian, Yi Zhou, Zaixiang Zheng, Yaoming Zhu, Zehui Lin, Jiangtao Feng, Shanbo Cheng, Lei Li, Mingxuan Wang, Hao Zhou
Abstract
This paper describes the Volctrans’ submission to the WMT21 news translation shared task for German->English translation. We build a parallel (i.e., non-autoregressive) translation system using the Glancing Transformer, which enables fast and accurate parallel decoding in contrast to the currently prevailing autoregressive models. To the best of our knowledge, this is the first parallel translation system that can be scaled to such a practical scenario like WMT competition. More importantly, our parallel translation system achieves the best BLEU score (35.0) on German->English translation task, outperforming all strong autoregressive counterparts.- Anthology ID:
- 2021.wmt-1.17
- Volume:
- Proceedings of the Sixth Conference on Machine Translation
- Month:
- November
- Year:
- 2021
- Address:
- Online
- Venue:
- WMT
- SIG:
- SIGMT
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 187–196
- Language:
- URL:
- https://aclanthology.org/2021.wmt-1.17
- DOI:
- Cite (ACL):
- Lihua Qian, Yi Zhou, Zaixiang Zheng, Yaoming Zhu, Zehui Lin, Jiangtao Feng, Shanbo Cheng, Lei Li, Mingxuan Wang, and Hao Zhou. 2021. The Volctrans GLAT System: Non-autoregressive Translation Meets WMT21. In Proceedings of the Sixth Conference on Machine Translation, pages 187–196, Online. Association for Computational Linguistics.
- Cite (Informal):
- The Volctrans GLAT System: Non-autoregressive Translation Meets WMT21 (Qian et al., WMT 2021)
- PDF:
- https://preview.aclanthology.org/remove-xml-comments/2021.wmt-1.17.pdf