The University of Maryland’s Chinese-English Neural Machine Translation Systems at WMT18

Weijia Xu, Marine Carpuat


Abstract
This paper describes the University of Maryland’s submission to the WMT 2018 Chinese↔English news translation tasks. Our systems are BPE-based self-attentional Transformer networks with parallel and backtranslated monolingual training data. Using ensembling and reranking, we improve over the Transformer baseline by +1.4 BLEU for Chinese→English and +3.97 BLEU for English→Chinese on newstest2017. Our best systems reach BLEU scores of 24.4 for Chinese→English and 39.0 for English→Chinese on newstest2018.
Anthology ID:
W18-6431
Volume:
Proceedings of the Third Conference on Machine Translation: Shared Task Papers
Month:
October
Year:
2018
Address:
Belgium, Brussels
Venue:
WMT
SIG:
SIGMT
Publisher:
Association for Computational Linguistics
Note:
Pages:
535–540
Language:
URL:
https://aclanthology.org/W18-6431
DOI:
10.18653/v1/W18-6431
Bibkey:
Cite (ACL):
Weijia Xu and Marine Carpuat. 2018. The University of Maryland’s Chinese-English Neural Machine Translation Systems at WMT18. In Proceedings of the Third Conference on Machine Translation: Shared Task Papers, pages 535–540, Belgium, Brussels. Association for Computational Linguistics.
Cite (Informal):
The University of Maryland’s Chinese-English Neural Machine Translation Systems at WMT18 (Xu & Carpuat, WMT 2018)
Copy Citation:
PDF:
https://preview.aclanthology.org/ingestion-script-update/W18-6431.pdf