Dynamic Phrase Tables for Machine Translation in an Interactive Post-editing Scenario

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

This paper presents a phrase table implementation for the Moses system that computes phrase table entries for phrase-based statistical machine translation (PBSMT) on demand by sampling an indexed bitext. While this approach has been used for years in hierarchical phrase-based translation, the PBSMT community has been slow to adopt this paradigm, due to concerns that this would be slow and lead to lower translation quality. The experiments conducted in the course of this work provide evidence to the contrary: without loss in translation quality, the sampling phrase table ranks second out of four in terms of speed, being slightly slower than hash table look-up (Junczys-Dowmunt, 2012) and considerably faster than current implementations of the approach suggested by Zens and Ney (2007). In addition, the underlying parallel corpus can be updated in real time, so that professionally produced translations can be used to improve the quality of the machine translation engine immediately.
Original languageEnglish
Title of host publicationProceedings of the Workshop on Interactive and Adaptive Machine Translation
Place of PublicationVancouver, BC, USA
PublisherAssociation for Machine Translation in the Americas, AMTA
Pages20-31
Number of pages12
Publication statusPublished - 2014
EventWORKSHOP ON INTERACTIVE AND ADAPTIVE MACHINE TRANSLATION - Vancouver, Canada
Duration: 22 Oct 201422 Oct 2014
http://www.statmt.org/iamt/

Conference

ConferenceWORKSHOP ON INTERACTIVE AND ADAPTIVE MACHINE TRANSLATION
Abbreviated titleAMTA 2014
CountryCanada
CityVancouver
Period22/10/1422/10/14
Internet address

Fingerprint Dive into the research topics of 'Dynamic Phrase Tables for Machine Translation in an Interactive Post-editing Scenario'. Together they form a unique fingerprint.

Cite this