Skip to main navigation Skip to search Skip to main content

A probabilistic approach to syntax-based reordering for statistical machine translation

  • Chi Ho Li*
  • , Dongdong Zhang
  • , Mu Li
  • , Ming Zhou
  • , Minghui Li
  • , Yi Guan
  • *Corresponding author for this work

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

Abstract

Inspired by previous preprocessing approaches to SMT, this paper proposes a novel, probabilistic approach to reordering which combines the merits of syntax and phrase-based SMT. Given a source sentence and its parse tree, our method generates, by tree operations, an n-best list of reordered inputs, which are then fed to standard phrase-based decoder to produce the optimal translation. Experiments show that, for the NIST MT-05 task of Chinese-to-English translation, the proposal leads to BLEU improvement of 1.56%.

Original languageEnglish
Title of host publicationACL 2007 - Proceedings of the 45th Annual Meeting of the Association for Computational Linguistics
Pages720-727
Number of pages8
StatePublished - 2007
Event45th Annual Meeting of the Association for Computational Linguistics, ACL 2007 - Prague, Czech Republic
Duration: 23 Jun 200730 Jun 2007

Publication series

NameACL 2007 - Proceedings of the 45th Annual Meeting of the Association for Computational Linguistics

Conference

Conference45th Annual Meeting of the Association for Computational Linguistics, ACL 2007
Country/TerritoryCzech Republic
CityPrague
Period23/06/0730/06/07

Fingerprint

Dive into the research topics of 'A probabilistic approach to syntax-based reordering for statistical machine translation'. Together they form a unique fingerprint.

Cite this