WeChat Neural Machine Translation Systems for WMT20

by   Fandong Meng, et al.

We participate in the WMT 2020 shared news translation task on Chinese to English. Our system is based on the Transformer (Vaswani et al., 2017a) with effective variants and the DTMT (Meng and Zhang, 2019) architecture. In our experiments, we employ data selection, several synthetic data generation approaches (i.e., back-translation, knowledge distillation, and iterative in-domain knowledge transfer), advanced finetuning approaches and self-bleu based model ensemble. Our constrained Chinese to English system achieves 36.9 case-sensitive BLEU score, which is the highest among all submissions.


WeChat Neural Machine Translation Systems for WMT21

This paper introduces WeChat AI's participation in WMT 2021 shared news ...

The NiuTrans Machine Translation Systems for WMT21

This paper describes NiuTrans neural machine translation systems of the ...

Shape of synth to come: Why we should use synthetic data for English surface realization

The Surface Realization Shared Tasks of 2018 and 2019 were Natural Langu...

The Volctrans Machine Translation System for WMT20

This paper describes our VolcTrans system on WMT20 shared news translati...

The University of Sydney's Machine Translation System for WMT19

This paper describes the University of Sydney's submission of the WMT 20...

Learning to Stop in Structured Prediction for Neural Machine Translation

Beam search optimization resolves many issues in neural machine translat...

Microsoft's Submission to the WMT2018 News Translation Task: How I Learned to Stop Worrying and Love the Data

This paper describes the Microsoft submission to the WMT2018 news transl...