Skip to main navigation Skip to search Skip to main content

Reordering with source language collocations

  • Zhanyi Liu*
  • , Haifeng Wang
  • , Hua Wu
  • , Ting Liu
  • , Sheng Li
  • *Corresponding author for this work
  • Harbin Institute of Technology
  • Baidu Inc

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

Abstract

This paper proposes a novel reordering model for statistical machine translation (SMT) by means of modeling the translation orders of the source language collocations. The model is learned from a word-aligned bilingual corpus where the collocated words in source sentences are automatically detected. During decoding, the model is employed to softly constrain the translation orders of the source language collocations, so as to constrain the translation orders of those source phrases containing these collocated words. The experimental results show that the proposed method significantly improves the translation quality, achieving the absolute improvements of 1.1∼1.4 BLEU score over the baseline methods.

Original languageEnglish
Title of host publicationACL-HLT 2011 - Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics
Subtitle of host publicationHuman Language Technologies
Pages1036-1044
Number of pages9
StatePublished - 2011
Event49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies, ACL-HLT 2011 - Portland, OR, United States
Duration: 19 Jun 201124 Jun 2011

Publication series

NameACL-HLT 2011 - Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies
Volume1

Conference

Conference49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies, ACL-HLT 2011
Country/TerritoryUnited States
CityPortland, OR
Period19/06/1124/06/11

Fingerprint

Dive into the research topics of 'Reordering with source language collocations'. Together they form a unique fingerprint.

Cite this