The Volctrans Machine Translation System for WMT20

Liwei Wu, Xiao Pan, Zehui Lin, Yaoming Zhu, Mingxuan Wang, Lei Li


Abstract
This paper describes our submission systems for VolcTrans for WMT20 shared news translation task. We participated in 8 translation directions. Our basic systems are based on Transformer (CITATION), into which we also employed new architectures (bigger or deeper Transformers, dynamic convolution). The final systems include text pre-process, subword(a.k.a. BPE(CITATION)), baseline model training, iterative back-translation, model ensemble, knowledge distillation and multilingual pre-training.
Anthology ID:
2020.wmt-1.33
Volume:
Proceedings of the Fifth Conference on Machine Translation
Month:
November
Year:
2020
Address:
Online
Editors:
Loïc Barrault, Ondřej Bojar, Fethi Bougares, Rajen Chatterjee, Marta R. Costa-jussà, Christian Federmann, Mark Fishel, Alexander Fraser, Yvette Graham, Paco Guzman, Barry Haddow, Matthias Huck, Antonio Jimeno Yepes, Philipp Koehn, André Martins, Makoto Morishita, Christof Monz, Masaaki Nagata, Toshiaki Nakazawa, Matteo Negri
Venue:
WMT
SIG:
SIGMT
Publisher:
Association for Computational Linguistics
Note:
Pages:
305–312
Language:
URL:
https://aclanthology.org/2020.wmt-1.33
DOI:
Bibkey:
Cite (ACL):
Liwei Wu, Xiao Pan, Zehui Lin, Yaoming Zhu, Mingxuan Wang, and Lei Li. 2020. The Volctrans Machine Translation System for WMT20. In Proceedings of the Fifth Conference on Machine Translation, pages 305–312, Online. Association for Computational Linguistics.
Cite (Informal):
The Volctrans Machine Translation System for WMT20 (Wu et al., WMT 2020)
Copy Citation:
PDF:
https://aclanthology.org/2020.wmt-1.33.pdf
Video:
 https://slideslive.com/38939581