Using shallow syntax information to improve word alignment and reordering for SMT

Josep M. Crego, Nizar Habash

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

Abstract

We describe two methods to improve SMT accuracy using shallow syntax information. First, we use chunks to refine the set of word alignments typically used as a starting point in SMT systems. Second, we extend an N -gram-based SMT system with chunk tags to better account for long-distance reorderings. Experiments are reported on an Arabic-English task showing significant improvements. A human error analysis indicates that long-distance reorderings are captured effectively.

Original languageEnglish (US)
Title of host publication3rd Workshop on Statistical Machine Translation, WMT 2008 at the Annual Meeting of the Association for Computational Linguistics, ACL 2008
PublisherAssociation for Computational Linguistics (ACL)
Pages53-61
Number of pages9
ISBN (Electronic)9781932432091
StatePublished - 2008
Event3rd Workshop on Statistical Machine Translation, WMT 2008 at the Annual Meeting of the Association for Computational Linguistics, ACL 2008 - Columbus, United States
Duration: Jun 19 2008 → …

Publication series

Name3rd Workshop on Statistical Machine Translation, WMT 2008 at the Annual Meeting of the Association for Computational Linguistics, ACL 2008

Conference

Conference3rd Workshop on Statistical Machine Translation, WMT 2008 at the Annual Meeting of the Association for Computational Linguistics, ACL 2008
Country/TerritoryUnited States
CityColumbus
Period6/19/08 → …

ASJC Scopus subject areas

  • Language and Linguistics
  • Linguistics and Language

Fingerprint

Dive into the research topics of 'Using shallow syntax information to improve word alignment and reordering for SMT'. Together they form a unique fingerprint.

Cite this