Skip to main navigation Skip to search Skip to main content

Lexicalized reordering model for hierarchical phrase-based translation

  • Microsoft USA

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

Lexicalized reordering model plays a central role in phrase-based statistical machine translation systems. The reordering model specifies the orientation for each phrase and calculates its probability conditioned on the phrase. In this paper, we describe the necessity and the challenge of introducing such a reordering model for hierarchical phrase-based translation. To deal with the challenge, we propose a novel lexicalized reordering model which is built directly on synchronous rules. For each target phrase contained in a rule, we calculate its orientation probability conditioned on the rule. We test our model on both small and large scale data. On NIST machine translation test sets, our reordering model achieved a 0.6-1.2 BLEU point improvements for Chinese-English translation over a strong baseline hierarchical phrase-based system.

Original languageEnglish
Title of host publicationCOLING 2014 - 25th International Conference on Computational Linguistics, Proceedings of COLING 2014
Subtitle of host publicationTechnical Papers
PublisherAssociation for Computational Linguistics, ACL Anthology
Pages1144-1153
Number of pages10
ISBN (Electronic)9781941643266
StatePublished - 2014
Event25th International Conference on Computational Linguistics, COLING 2014 - Dublin, Ireland
Duration: 23 Aug 201429 Aug 2014

Publication series

NameCOLING 2014 - 25th International Conference on Computational Linguistics, Proceedings of COLING 2014: Technical Papers

Conference

Conference25th International Conference on Computational Linguistics, COLING 2014
Country/TerritoryIreland
CityDublin
Period23/08/1429/08/14

Fingerprint

Dive into the research topics of 'Lexicalized reordering model for hierarchical phrase-based translation'. Together they form a unique fingerprint.

Cite this