Microsoft Research Asia’s Systems for WMT19

Yingce Xia, Xu Tan, Fei Tian, Fei Gao, Di He, Weicong Chen, Yang Fan, Linyuan Gong, Yichong Leng, Renqian Luo, Yiren Wang, Lijun Wu, Jinhua Zhu, Tao Qin, Tie-Yan Liu


Abstract
We Microsoft Research Asia made submissions to 11 language directions in the WMT19 news translation tasks. We won the first place for 8 of the 11 directions and the second place for the other three. Our basic systems are built on Transformer, back translation and knowledge distillation. We integrate several of our rececent techniques to enhance the baseline systems: multi-agent dual learning (MADL), masked sequence-to-sequence pre-training (MASS), neural architecture optimization (NAO), and soft contextual data augmentation (SCA).
Anthology ID:
W19-5348
Volume:
Proceedings of the Fourth Conference on Machine Translation (Volume 2: Shared Task Papers, Day 1)
Month:
August
Year:
2019
Address:
Florence, Italy
Venues:
ACL | WMT | WS
SIG:
SIGMT
Publisher:
Association for Computational Linguistics
Note:
Pages:
424–433
Language:
URL:
https://aclanthology.org/W19-5348
DOI:
10.18653/v1/W19-5348
Bibkey:
Cite (ACL):
Yingce Xia, Xu Tan, Fei Tian, Fei Gao, Di He, Weicong Chen, Yang Fan, Linyuan Gong, Yichong Leng, Renqian Luo, Yiren Wang, Lijun Wu, Jinhua Zhu, Tao Qin, and Tie-Yan Liu. 2019. Microsoft Research Asia’s Systems for WMT19. In Proceedings of the Fourth Conference on Machine Translation (Volume 2: Shared Task Papers, Day 1), pages 424–433, Florence, Italy. Association for Computational Linguistics.
Cite (Informal):
Microsoft Research Asia’s Systems for WMT19 (Xia et al., 2019)
Copy Citation:
PDF:
https://aclanthology.org/W19-5348.pdf
Data
ASIRRA