Sentence level dialect identification for machine translation system selection

Wael Salloum, Heba Elfardy, Linda Alamir-Salloum, Nizar Habash, Mona Diab

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

Abstract

In this paper we study the use of sentence-level dialect identification in optimizing machine translation system selection when translating mixed dialect input. We test our approach on Arabic, a prototypical diglossic language; and we optimize the combination of four different machine translation systems. Our best result improves over the best single MT system baseline by 1.0% BLEU and over a strong system selection baseline by 0.6% BLEU on a blind test set.

Original languageEnglish (US)
Title of host publicationLong Papers
PublisherAssociation for Computational Linguistics (ACL)
Pages772-778
Number of pages7
Volume2
ISBN (Print)9781937284732
StatePublished - Jan 1 2014
Event52nd Annual Meeting of the Association for Computational Linguistics, ACL 2014 - Baltimore, MD, United States
Duration: Jun 22 2014Jun 27 2014

Other

Other52nd Annual Meeting of the Association for Computational Linguistics, ACL 2014
CountryUnited States
CityBaltimore, MD
Period6/22/146/27/14

Fingerprint

dialect
Machine Translation System
language
Diglossic
Blind Test
Language
Translating

ASJC Scopus subject areas

  • Language and Linguistics
  • Linguistics and Language

Cite this

Salloum, W., Elfardy, H., Alamir-Salloum, L., Habash, N., & Diab, M. (2014). Sentence level dialect identification for machine translation system selection. In Long Papers (Vol. 2, pp. 772-778). Association for Computational Linguistics (ACL).

Sentence level dialect identification for machine translation system selection. / Salloum, Wael; Elfardy, Heba; Alamir-Salloum, Linda; Habash, Nizar; Diab, Mona.

Long Papers. Vol. 2 Association for Computational Linguistics (ACL), 2014. p. 772-778.

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

Salloum, W, Elfardy, H, Alamir-Salloum, L, Habash, N & Diab, M 2014, Sentence level dialect identification for machine translation system selection. in Long Papers. vol. 2, Association for Computational Linguistics (ACL), pp. 772-778, 52nd Annual Meeting of the Association for Computational Linguistics, ACL 2014, Baltimore, MD, United States, 6/22/14.
Salloum W, Elfardy H, Alamir-Salloum L, Habash N, Diab M. Sentence level dialect identification for machine translation system selection. In Long Papers. Vol. 2. Association for Computational Linguistics (ACL). 2014. p. 772-778
Salloum, Wael ; Elfardy, Heba ; Alamir-Salloum, Linda ; Habash, Nizar ; Diab, Mona. / Sentence level dialect identification for machine translation system selection. Long Papers. Vol. 2 Association for Computational Linguistics (ACL), 2014. pp. 772-778
@inproceedings{d7e86c5695974768becb98bbd13be1a8,
title = "Sentence level dialect identification for machine translation system selection",
abstract = "In this paper we study the use of sentence-level dialect identification in optimizing machine translation system selection when translating mixed dialect input. We test our approach on Arabic, a prototypical diglossic language; and we optimize the combination of four different machine translation systems. Our best result improves over the best single MT system baseline by 1.0{\%} BLEU and over a strong system selection baseline by 0.6{\%} BLEU on a blind test set.",
author = "Wael Salloum and Heba Elfardy and Linda Alamir-Salloum and Nizar Habash and Mona Diab",
year = "2014",
month = "1",
day = "1",
language = "English (US)",
isbn = "9781937284732",
volume = "2",
pages = "772--778",
booktitle = "Long Papers",
publisher = "Association for Computational Linguistics (ACL)",

}

TY - GEN

T1 - Sentence level dialect identification for machine translation system selection

AU - Salloum, Wael

AU - Elfardy, Heba

AU - Alamir-Salloum, Linda

AU - Habash, Nizar

AU - Diab, Mona

PY - 2014/1/1

Y1 - 2014/1/1

N2 - In this paper we study the use of sentence-level dialect identification in optimizing machine translation system selection when translating mixed dialect input. We test our approach on Arabic, a prototypical diglossic language; and we optimize the combination of four different machine translation systems. Our best result improves over the best single MT system baseline by 1.0% BLEU and over a strong system selection baseline by 0.6% BLEU on a blind test set.

AB - In this paper we study the use of sentence-level dialect identification in optimizing machine translation system selection when translating mixed dialect input. We test our approach on Arabic, a prototypical diglossic language; and we optimize the combination of four different machine translation systems. Our best result improves over the best single MT system baseline by 1.0% BLEU and over a strong system selection baseline by 0.6% BLEU on a blind test set.

UR - http://www.scopus.com/inward/record.url?scp=84906932173&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84906932173&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:84906932173

SN - 9781937284732

VL - 2

SP - 772

EP - 778

BT - Long Papers

PB - Association for Computational Linguistics (ACL)

ER -