Fixed length word suffix for Factored Statistical Machine Translation

Narges Sharif Razavian, Stephan Vogel

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

3 Citations (Scopus)

Abstract

Factored Statistical Machine Translation extends the Phrase Based SMT model by allowing each word to be a vector of factors. Experiments have shown effectiveness of many factors, including the Part of Speech tags in improving the grammaticality of the output. However, high quality part of speech taggers are not available in open domain for many languages. In this paper we used fixed length word suffix as a new factor in the Factored SMT, and were able to achieve significant improvements in three set of experiments: large NIST Arabic to English system, medium WMT Spanish to English system, and small TRANSTAC English to Iraqi system.

Original languageEnglish
Title of host publicationACL 2010 - 48th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference
Pages147-150
Number of pages4
Publication statusPublished - 1 Dec 2010
Externally publishedYes
Event48th Annual Meeting of the Association for Computational Linguistics, ACL 2010 - Uppsala, Sweden
Duration: 11 Jul 201016 Jul 2010

Other

Other48th Annual Meeting of the Association for Computational Linguistics, ACL 2010
CountrySweden
CityUppsala
Period11/7/1016/7/10

Fingerprint

media system
experiment
language
Word Length
Statistical Machine Translation
Part of Speech
Experiment
Grammaticality
Media System
Language
Tag

ASJC Scopus subject areas

  • Language and Linguistics
  • Linguistics and Language

Cite this

Razavian, N. S., & Vogel, S. (2010). Fixed length word suffix for Factored Statistical Machine Translation. In ACL 2010 - 48th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (pp. 147-150)

Fixed length word suffix for Factored Statistical Machine Translation. / Razavian, Narges Sharif; Vogel, Stephan.

ACL 2010 - 48th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference. 2010. p. 147-150.

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

Razavian, NS & Vogel, S 2010, Fixed length word suffix for Factored Statistical Machine Translation. in ACL 2010 - 48th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference. pp. 147-150, 48th Annual Meeting of the Association for Computational Linguistics, ACL 2010, Uppsala, Sweden, 11/7/10.
Razavian NS, Vogel S. Fixed length word suffix for Factored Statistical Machine Translation. In ACL 2010 - 48th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference. 2010. p. 147-150
Razavian, Narges Sharif ; Vogel, Stephan. / Fixed length word suffix for Factored Statistical Machine Translation. ACL 2010 - 48th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference. 2010. pp. 147-150
@inproceedings{9c8ab68db02c40668c69e5532a48791b,
title = "Fixed length word suffix for Factored Statistical Machine Translation",
abstract = "Factored Statistical Machine Translation extends the Phrase Based SMT model by allowing each word to be a vector of factors. Experiments have shown effectiveness of many factors, including the Part of Speech tags in improving the grammaticality of the output. However, high quality part of speech taggers are not available in open domain for many languages. In this paper we used fixed length word suffix as a new factor in the Factored SMT, and were able to achieve significant improvements in three set of experiments: large NIST Arabic to English system, medium WMT Spanish to English system, and small TRANSTAC English to Iraqi system.",
author = "Razavian, {Narges Sharif} and Stephan Vogel",
year = "2010",
month = "12",
day = "1",
language = "English",
isbn = "9781617388088",
pages = "147--150",
booktitle = "ACL 2010 - 48th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference",

}

TY - GEN

T1 - Fixed length word suffix for Factored Statistical Machine Translation

AU - Razavian, Narges Sharif

AU - Vogel, Stephan

PY - 2010/12/1

Y1 - 2010/12/1

N2 - Factored Statistical Machine Translation extends the Phrase Based SMT model by allowing each word to be a vector of factors. Experiments have shown effectiveness of many factors, including the Part of Speech tags in improving the grammaticality of the output. However, high quality part of speech taggers are not available in open domain for many languages. In this paper we used fixed length word suffix as a new factor in the Factored SMT, and were able to achieve significant improvements in three set of experiments: large NIST Arabic to English system, medium WMT Spanish to English system, and small TRANSTAC English to Iraqi system.

AB - Factored Statistical Machine Translation extends the Phrase Based SMT model by allowing each word to be a vector of factors. Experiments have shown effectiveness of many factors, including the Part of Speech tags in improving the grammaticality of the output. However, high quality part of speech taggers are not available in open domain for many languages. In this paper we used fixed length word suffix as a new factor in the Factored SMT, and were able to achieve significant improvements in three set of experiments: large NIST Arabic to English system, medium WMT Spanish to English system, and small TRANSTAC English to Iraqi system.

UR - http://www.scopus.com/inward/record.url?scp=84859975507&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84859975507&partnerID=8YFLogxK

M3 - Conference contribution

SN - 9781617388088

SP - 147

EP - 150

BT - ACL 2010 - 48th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference

ER -