Can Markov models over minimal translation units help phrase-based SMT?

Nadir Durrani, Alexander Fraser, Helmut Schmid, Hieu Hoang, Philipp Koehn

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

23 Citations (Scopus)

Abstract

The phrase-based and N-gram-based SMT frameworks complement each other. While the former is better able to memorize, the latter provides a more principled model that captures dependencies across phrasal boundaries. Some work has been done to combine insights from these two frameworks. A recent successful attempt showed the advantage of using phrase-based search on top of an N-gram-based model. We probe this question in the reverse direction by investigating whether integrating N-gram-based translation and reordering models into a phrase-based decoder helps overcome the problematic phrasal independence assumption. A large scale evaluation over 8 language pairs shows that performance does significantly improve.

Original languageEnglish
Title of host publicationACL 2013 - 51st Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference
PublisherAssociation for Computational Linguistics (ACL)
Pages399-405
Number of pages7
Volume2
ISBN (Print)9781937284510
Publication statusPublished - 2013
Externally publishedYes
Event51st Annual Meeting of the Association for Computational Linguistics, ACL 2013 - Sofia, Bulgaria
Duration: 4 Aug 20139 Aug 2013

Other

Other51st Annual Meeting of the Association for Computational Linguistics, ACL 2013
CountryBulgaria
CitySofia
Period4/8/139/8/13

    Fingerprint

ASJC Scopus subject areas

  • Language and Linguistics
  • Linguistics and Language

Cite this

Durrani, N., Fraser, A., Schmid, H., Hoang, H., & Koehn, P. (2013). Can Markov models over minimal translation units help phrase-based SMT? In ACL 2013 - 51st Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Vol. 2, pp. 399-405). Association for Computational Linguistics (ACL).