The NiuTrans Machine Translation System for WMT18

Qiang Wang, Bei Li, Jiqiang Liu, Bojian Jiang, Zheyang Zhang, Yinqiao Li, Ye Lin, Tong Xiao, Jingbo Zhu


Abstract
This paper describes the submission of the NiuTrans neural machine translation system for the WMT 2018 Chinese ↔ English news translation tasks. Our baseline systems are based on the Transformer architecture. We further improve the translation performance 2.4-2.6 BLEU points from four aspects, including architectural improvements, diverse ensemble decoding, reranking, and post-processing. Among constrained submissions, we rank 2nd out of 16 submitted systems on Chinese → English task and 3rd out of 16 on English → Chinese task, respectively.
Anthology ID:
W18-6430
Volume:
Proceedings of the Third Conference on Machine Translation: Shared Task Papers
Month:
October
Year:
2018
Address:
Belgium, Brussels
Venues:
EMNLP | WMT | WS
SIG:
SIGMT
Publisher:
Association for Computational Linguistics
Note:
Pages:
528–534
Language:
URL:
https://www.aclweb.org/anthology/W18-6430
DOI:
10.18653/v1/W18-6430
Bib Export formats:
BibTeX MODS XML EndNote
PDF:
http://aclanthology.lst.uni-saarland.de/W18-6430.pdf