SOTAVerified

The NiuTrans Machine Translation Systems for WMT21

2021-09-22WMT (EMNLP) 2021Unverified0· sign in to hype

Shuhan Zhou, Tao Zhou, Binghao Wei, Yingfeng Luo, Yongyu Mu, Zefan Zhou, Chenglong Wang, Xuanjun Zhou, Chuanhao Lv, Yi Jing, Laohu Wang, Jingnan Zhang, Canan Huang, Zhongxiang Yan, Chi Hu, Bei Li, Tong Xiao, Jingbo Zhu

Unverified — Be the first to reproduce this paper.

Reproduce

Abstract

This paper describes NiuTrans neural machine translation systems of the WMT 2021 news translation tasks. We made submissions to 9 language directions, including English , Japanese, Russian, Icelandic\ and EnglishHausa tasks. Our primary systems are built on several effective variants of Transformer, e.g., Transformer-DLCL, ODE-Transformer. We also utilize back-translation, knowledge distillation, post-ensemble, and iterative fine-tuning techniques to enhance the model performance further.

Tasks

Reproductions