Microsoft Research Asia's Systems for WMT19

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).

PDF Abstract WS 2019 PDF WS 2019 Abstract

Datasets


Introduced in the Paper:

ASIRRA

Results from the Paper


  Submit results from this paper to get state-of-the-art GitHub badges and help the community compare results to other papers.

Methods