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
Editors:
Loic Barrault, Ondrej Bojar, Fethi Bougares, Rajen Chatterjee, Marta R. Costa-jussa, Christian Federmann, Mark Fishel, Alexander Fraser, Markus Freitag, Yvette Graham, Roman Grundkiewicz, Paco Guzman, Barry Haddow, Matthias Huck, Antonio Jimeno Yepes, Philipp Koehn, Tom Kocmi, Andre Martins, Makoto Morishita, Christof Monz
Venue:
WMT
SIG:
SIGMT
Publisher:
Association for Computational Linguistics
Note:
Pages:
187–196
Language:
URL:
https://preview.aclanthology.org/build-pipeline-with-new-library/2021.wmt-1.17/
DOI:
Bibkey:
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)
Copy Citation:
PDF:
https://preview.aclanthology.org/build-pipeline-with-new-library/2021.wmt-1.17.pdf