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).
@article{arxiv.1911.06191,
title = {Microsoft Research Asia's Systems for WMT19},
author = {Yingce Xia and Xu Tan and Fei Tian and Fei Gao and Weicong Chen and Yang Fan and Linyuan Gong and Yichong Leng and Renqian Luo and Yiren Wang and Lijun Wu and Jinhua Zhu and Tao Qin and Tie-Yan Liu},
journal= {arXiv preprint arXiv:1911.06191},
year = {2019}
}
Comments
Accepted to "Fourth Conference on Machine Translation (WMT19)"