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

21 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

language
evaluation
performance
Translation Units
N-gram
Markov Model
Evaluation
Language

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).

Can Markov models over minimal translation units help phrase-based SMT? / Durrani, Nadir; Fraser, Alexander; Schmid, Helmut; Hoang, Hieu; Koehn, Philipp.

ACL 2013 - 51st Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference. Vol. 2 Association for Computational Linguistics (ACL), 2013. p. 399-405.

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

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, Association for Computational Linguistics (ACL), pp. 399-405, 51st Annual Meeting of the Association for Computational Linguistics, ACL 2013, Sofia, Bulgaria, 4/8/13.
Durrani N, Fraser A, Schmid H, Hoang H, Koehn P. 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. Association for Computational Linguistics (ACL). 2013. p. 399-405
Durrani, Nadir ; Fraser, Alexander ; Schmid, Helmut ; Hoang, Hieu ; Koehn, Philipp. / Can Markov models over minimal translation units help phrase-based SMT?. ACL 2013 - 51st Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference. Vol. 2 Association for Computational Linguistics (ACL), 2013. pp. 399-405
@inproceedings{32bf4595bda04a1b9747336dc00ccc2a,
title = "Can Markov models over minimal translation units help phrase-based SMT?",
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.",
author = "Nadir Durrani and Alexander Fraser and Helmut Schmid and Hieu Hoang and Philipp Koehn",
year = "2013",
language = "English",
isbn = "9781937284510",
volume = "2",
pages = "399--405",
booktitle = "ACL 2013 - 51st Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference",
publisher = "Association for Computational Linguistics (ACL)",

}

TY - GEN

T1 - Can Markov models over minimal translation units help phrase-based SMT?

AU - Durrani, Nadir

AU - Fraser, Alexander

AU - Schmid, Helmut

AU - Hoang, Hieu

AU - Koehn, Philipp

PY - 2013

Y1 - 2013

N2 - 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.

AB - 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.

UR - http://www.scopus.com/inward/record.url?scp=84907307781&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84907307781&partnerID=8YFLogxK

M3 - Conference contribution

SN - 9781937284510

VL - 2

SP - 399

EP - 405

BT - ACL 2013 - 51st Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference

PB - Association for Computational Linguistics (ACL)

ER -