Faster and Lighter Phrase-based Machine Translation Baseline

Liling Tan


Abstract
This paper describes the SENSE machine translation system participation in the Third Workshop for Asian Translation (WAT2016). We share our best practices to build a fast and light phrase-based machine translation (PBMT) models that have comparable results to the baseline systems provided by the organizers. As Neural Machine Translation (NMT) overtakes PBMT as the state-of-the-art, deep learning and new MT practitioners might not be familiar with the PBMT paradigm and we hope that this paper will help them build a PBMT baseline system quickly and easily.
Anthology ID:
W16-4618
Volume:
Proceedings of the 3rd Workshop on Asian Translation (WAT2016)
Month:
December
Year:
2016
Address:
Osaka, Japan
Venues:
WAT | WS
SIG:
Publisher:
The COLING 2016 Organizing Committee
Note:
Pages:
184–193
Language:
URL:
https://aclanthology.org/W16-4618
DOI:
Bibkey:
Cite (ACL):
Liling Tan. 2016. Faster and Lighter Phrase-based Machine Translation Baseline. In Proceedings of the 3rd Workshop on Asian Translation (WAT2016), pages 184–193, Osaka, Japan. The COLING 2016 Organizing Committee.
Cite (Informal):
Faster and Lighter Phrase-based Machine Translation Baseline (Tan, 2016)
Copy Citation:
PDF:
https://aclanthology.org/W16-4618.pdf