Fast, Scalable Phrase-Based SMT Decoding

Hieu Hoang, Nikolay Bogoychev, Lane Schwartz, Marcin Junczys-Dowmunt


Abstract
The utilization of statistical machine translation (SMT) has grown enormously over the last decade, many using open-source software developed by the NLP community. As commercial use has increased, there is need for software that is optimized for commercial requirements, in particular, fast phrase-based decoding and more efficient utilization of modern multicore servers. In this paper we re-examine the major components of phrase-based decoding and decoder implementation with particular emphasis on speed and scalability on multicore machines. The result is a drop-in replacement for the Moses decoder which is up to fifteen times faster and scales monotonically with the number of cores.
Anthology ID:
2016.amta-researchers.4
Volume:
Conferences of the Association for Machine Translation in the Americas: MT Researchers' Track
Month:
October 28 - November 1
Year:
2016
Address:
Austin, TX, USA
Venue:
AMTA
SIG:
Publisher:
The Association for Machine Translation in the Americas
Note:
Pages:
40–52
Language:
URL:
https://aclanthology.org/2016.amta-researchers.4
DOI:
Bibkey:
Cite (ACL):
Hieu Hoang, Nikolay Bogoychev, Lane Schwartz, and Marcin Junczys-Dowmunt. 2016. Fast, Scalable Phrase-Based SMT Decoding. In Conferences of the Association for Machine Translation in the Americas: MT Researchers' Track, pages 40–52, Austin, TX, USA. The Association for Machine Translation in the Americas.
Cite (Informal):
Fast, Scalable Phrase-Based SMT Decoding (Hoang et al., AMTA 2016)
Copy Citation:
PDF:
https://preview.aclanthology.org/paclic-22-ingestion/2016.amta-researchers.4.pdf