Fast, Scalable Phrase-Based SMT Decoding

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

Fast, Scalable Phrase-Based SMT Decoding

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

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

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.

Original language	English (US)
Title of host publication	MT Researchers' Track
Editors	Spence Green, Lane Schwartz
Publisher	Association for Machine Translation in the Americas
Pages	40-52
Number of pages	13
ISBN (Electronic)	9780000000002
State	Published - 2016
Event	12th Conference of the Association for Machine Translation in the Americas, AMTA 2016 - Austin, United States Duration: Oct 28 2016 → Nov 1 2016

Publication series

Name	Proceedings - AMTA 2016: 12th Conference of the Association for Machine Translation in the Americas
Volume	1

Conference

Conference	12th Conference of the Association for Machine Translation in the Americas, AMTA 2016
Country/Territory	United States
City	Austin
Period	10/28/16 → 11/1/16

ASJC Scopus subject areas

Human-Computer Interaction
Software
Language and Linguistics

Library availability

Discover UIUC Full Text

Cite this

Fast, Scalable Phrase-Based SMT Decoding. / Hoang, Hieu; Bogoychev, Nikolay; Schwartz, Lane et al.
MT Researchers' Track. ed. / Spence Green; Lane Schwartz. Association for Machine Translation in the Americas, 2016. p. 40-52 (Proceedings - AMTA 2016: 12th Conference of the Association for Machine Translation in the Americas; Vol. 1).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Hoang, H, Bogoychev, N, Schwartz, L & Junczys-Dowmunt, M 2016, Fast, Scalable Phrase-Based SMT Decoding. in S Green & L Schwartz (eds), MT Researchers' Track. Proceedings - AMTA 2016: 12th Conference of the Association for Machine Translation in the Americas, vol. 1, Association for Machine Translation in the Americas, pp. 40-52, 12th Conference of the Association for Machine Translation in the Americas, AMTA 2016, Austin, United States, 10/28/16.

@inproceedings{32022d02a39348319803b1aa64aa742c,

title = "Fast, Scalable Phrase-Based SMT Decoding",

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.",

author = "Hieu Hoang and Nikolay Bogoychev and Lane Schwartz and Marcin Junczys-Dowmunt",

note = "Publisher Copyright: {\textcopyright} 2016 The Authors.; 12th Conference of the Association for Machine Translation in the Americas, AMTA 2016 ; Conference date: 28-10-2016 Through 01-11-2016",

year = "2016",

language = "English (US)",

series = "Proceedings - AMTA 2016: 12th Conference of the Association for Machine Translation in the Americas",

publisher = "Association for Machine Translation in the Americas",

pages = "40--52",

editor = "Spence Green and Lane Schwartz",

booktitle = "MT Researchers' Track",

}

TY - GEN

T1 - Fast, Scalable Phrase-Based SMT Decoding

AU - Hoang, Hieu

AU - Bogoychev, Nikolay

AU - Schwartz, Lane

AU - Junczys-Dowmunt, Marcin

PY - 2016

Y1 - 2016

N2 - 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.

AB - 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.

UR - http://www.scopus.com/inward/record.url?scp=85072939955&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85072939955&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:85072939955

T3 - Proceedings - AMTA 2016: 12th Conference of the Association for Machine Translation in the Americas

SP - 40

EP - 52

BT - MT Researchers' Track

A2 - Green, Spence

A2 - Schwartz, Lane

PB - Association for Machine Translation in the Americas

T2 - 12th Conference of the Association for Machine Translation in the Americas, AMTA 2016

Y2 - 28 October 2016 through 1 November 2016

ER -

Fast, Scalable Phrase-Based SMT Decoding

Abstract

Publication series

Conference

ASJC Scopus subject areas

Library availability

Related links

Fingerprint

Cite this