An Empirical Study of Machine Translation for the Shared Task of WMT18

Chao Bei, Hao Zong, Yiming Wang, Baoyong Fan, Shiqi Li, Conghu Yuan


Abstract
This paper describes the Global Tone Communication Co., Ltd.’s submission of the WMT18 shared news translation task. We participated in the English-to-Chinese direction and get the best BLEU (43.8) scores among all the participants. The submitted system focus on data clearing and techniques to build a competitive model for this task. Unlike other participants, the submitted system are mainly relied on the data filtering to obtain the best BLEU score. We do data filtering not only for provided sentences but also for the back translated sentences. The techniques we apply for data filtering include filtering by rules, language models and translation models. We also conduct several experiments to validate the effectiveness of training techniques. According to our experiments, the Annealing Adam optimizing function and ensemble decoding are the most effective techniques for the model training.
Anthology ID:
W18-6404
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:
340–344
Language:
URL:
https://www.aclweb.org/anthology/W18-6404
DOI:
10.18653/v1/W18-6404
Bib Export formats:
BibTeX MODS XML EndNote
PDF:
http://aclanthology.lst.uni-saarland.de/W18-6404.pdf