Pith. sign in

REVIEW

Microsoft Research Asia's Systems for WMT19

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 1911.06191 v1 pith:J6GA7CUL submitted 2019-11-07 cs.CL cs.LGstat.ML

Yingce Xia , Xu Tan , Fei Tian , Fei Gao , Weicong Chen , Yang Fan , Linyuan Gong , Yichong Leng
show 6 more authors
Renqian Luo Yiren Wang Lijun Wu Jinhua Zhu Tao Qin Tie-Yan Liu
This is my paper · ORCID
classification cs.CLcs.LGstat.ML
keywords systemsasiadirectionsmicrosoftplaceresearchtranslationwmt19
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original 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).

Discussion (0). Continue with ORCID to comment.

Pith tools