This paper describes the Volctrans' submission to the WMT21 news translation shared task for German->English translation. We build a parallel (i.e., non-autoregressive) translation system using the Glancing Transformer, which enables fast and accurate parallel decoding in contrast to the currently prevailing autoregressive models. To the best of our knowledge, this is the first parallel translation system that can be scaled to such a practical scenario like WMT competition. More importantly, our parallel translation system achieves the best BLEU score (35.0) on German->English translation task, outperforming all strong autoregressive counterparts.
@article{arxiv.2109.11247,
title = {The Volctrans GLAT System: Non-autoregressive Translation Meets WMT21},
author = {Lihua Qian and Yi Zhou and Zaixiang Zheng and Yaoming Zhu and Zehui Lin and Jiangtao Feng and Shanbo Cheng and Lei Li and Mingxuan Wang and Hao Zhou},
journal= {arXiv preprint arXiv:2109.11247},
year = {2021}
}