Four techniques for online handling of out-of-vocabularywords in Arabic-English statistical machine translation

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

Abstract

We present four techniques for online handling of Out-of-Vocabulary words in Phrasebased Statistical Machine Translation. The techniques use spelling expansion, morphological expansion, dictionary term expansion and proper name transliteration to reuse or extend a phrase table. We compare the performance of these techniques and combine them. Our results show a consistent improvement over a state-of-the-art baseline in terms of BLEU and a manual error analysis.

Original languageEnglish (US)
Title of host publicationACL-08
Subtitle of host publicationHLT - 46th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies, Proceedings of the Conference
Pages57-60
Number of pages4
StatePublished - Dec 1 2008
Event46th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies, ACL-08: HLT - Columbus, OH, United States
Duration: Jun 15 2008Jun 20 2008

Other

Other46th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies, ACL-08: HLT
CountryUnited States
CityColumbus, OH
Period6/15/086/20/08

Fingerprint

dictionary
vocabulary
performance
Glossaries
Error analysis
Statistical Machine Translation
Spelling
Transliteration
Proper Names
Dictionary
Reuse
Vocabulary
Error Analysis

ASJC Scopus subject areas

  • Language and Linguistics
  • Computer Networks and Communications
  • Linguistics and Language

Cite this

Habash, N. (2008). Four techniques for online handling of out-of-vocabularywords in Arabic-English statistical machine translation. In ACL-08: HLT - 46th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies, Proceedings of the Conference (pp. 57-60)

Four techniques for online handling of out-of-vocabularywords in Arabic-English statistical machine translation. / Habash, Nizar.

ACL-08: HLT - 46th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies, Proceedings of the Conference. 2008. p. 57-60.

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

Habash, N 2008, Four techniques for online handling of out-of-vocabularywords in Arabic-English statistical machine translation. in ACL-08: HLT - 46th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies, Proceedings of the Conference. pp. 57-60, 46th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies, ACL-08: HLT, Columbus, OH, United States, 6/15/08.
Habash N. Four techniques for online handling of out-of-vocabularywords in Arabic-English statistical machine translation. In ACL-08: HLT - 46th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies, Proceedings of the Conference. 2008. p. 57-60
Habash, Nizar. / Four techniques for online handling of out-of-vocabularywords in Arabic-English statistical machine translation. ACL-08: HLT - 46th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies, Proceedings of the Conference. 2008. pp. 57-60
@inproceedings{db57f96fa12f46e98da118ccd5d10eab,
title = "Four techniques for online handling of out-of-vocabularywords in Arabic-English statistical machine translation",
abstract = "We present four techniques for online handling of Out-of-Vocabulary words in Phrasebased Statistical Machine Translation. The techniques use spelling expansion, morphological expansion, dictionary term expansion and proper name transliteration to reuse or extend a phrase table. We compare the performance of these techniques and combine them. Our results show a consistent improvement over a state-of-the-art baseline in terms of BLEU and a manual error analysis.",
author = "Nizar Habash",
year = "2008",
month = "12",
day = "1",
language = "English (US)",
isbn = "9781932432046",
pages = "57--60",
booktitle = "ACL-08",

}

TY - GEN

T1 - Four techniques for online handling of out-of-vocabularywords in Arabic-English statistical machine translation

AU - Habash, Nizar

PY - 2008/12/1

Y1 - 2008/12/1

N2 - We present four techniques for online handling of Out-of-Vocabulary words in Phrasebased Statistical Machine Translation. The techniques use spelling expansion, morphological expansion, dictionary term expansion and proper name transliteration to reuse or extend a phrase table. We compare the performance of these techniques and combine them. Our results show a consistent improvement over a state-of-the-art baseline in terms of BLEU and a manual error analysis.

AB - We present four techniques for online handling of Out-of-Vocabulary words in Phrasebased Statistical Machine Translation. The techniques use spelling expansion, morphological expansion, dictionary term expansion and proper name transliteration to reuse or extend a phrase table. We compare the performance of these techniques and combine them. Our results show a consistent improvement over a state-of-the-art baseline in terms of BLEU and a manual error analysis.

UR - http://www.scopus.com/inward/record.url?scp=80053399448&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=80053399448&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:80053399448

SN - 9781932432046

SP - 57

EP - 60

BT - ACL-08

ER -