Translating dialectal arabic to english

Hassan Sajjad, Kareem Darwish, Yonatan Belinkov

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

15 Citations (Scopus)

Abstract

We present a dialectal Egyptian Arabic to English statistical machine translation system that leverages dialectal to Modern Standard Arabic (MSA) adaptation. In contrast to previous work, we first narrow down the gap between Egyptian and MSA by applying an automatic characterlevel transformational model that changes Egyptian to EG', which looks similar to MSA. The transformations include morphological, phonological and spelling changes. The transformation reduces the out-of-vocabulary (OOV) words from 5.2% to 2.6% and gives a gain of 1.87 BLEU points. Further, adapting large MSA/English parallel data increases the lexical coverage, reduces OOVs to 0.7% and leads to an absolute BLEU improvement of 2.73 points.

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)
Pages1-6
Number of pages6
Volume2
ISBN (Print)9781937284510
Publication statusPublished - 1 Jan 2013
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

vocabulary
coverage
Translating
Egyptians
Spelling
Machine Translation System
Statistical Machine Translation
Vocabulary

ASJC Scopus subject areas

  • Language and Linguistics
  • Linguistics and Language

Cite this

Sajjad, H., Darwish, K., & Belinkov, Y. (2013). Translating dialectal arabic to english. In ACL 2013 - 51st Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Vol. 2, pp. 1-6). Association for Computational Linguistics (ACL).

Translating dialectal arabic to english. / Sajjad, Hassan; Darwish, Kareem; Belinkov, Yonatan.

ACL 2013 - 51st Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference. Vol. 2 Association for Computational Linguistics (ACL), 2013. p. 1-6.

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

Sajjad, H, Darwish, K & Belinkov, Y 2013, Translating dialectal arabic to english. in ACL 2013 - 51st Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference. vol. 2, Association for Computational Linguistics (ACL), pp. 1-6, 51st Annual Meeting of the Association for Computational Linguistics, ACL 2013, Sofia, Bulgaria, 4/8/13.
Sajjad H, Darwish K, Belinkov Y. Translating dialectal arabic to english. 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. 1-6
Sajjad, Hassan ; Darwish, Kareem ; Belinkov, Yonatan. / Translating dialectal arabic to english. ACL 2013 - 51st Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference. Vol. 2 Association for Computational Linguistics (ACL), 2013. pp. 1-6
@inproceedings{a81c4f08914041ba877a8c818b380a22,
title = "Translating dialectal arabic to english",
abstract = "We present a dialectal Egyptian Arabic to English statistical machine translation system that leverages dialectal to Modern Standard Arabic (MSA) adaptation. In contrast to previous work, we first narrow down the gap between Egyptian and MSA by applying an automatic characterlevel transformational model that changes Egyptian to EG', which looks similar to MSA. The transformations include morphological, phonological and spelling changes. The transformation reduces the out-of-vocabulary (OOV) words from 5.2{\%} to 2.6{\%} and gives a gain of 1.87 BLEU points. Further, adapting large MSA/English parallel data increases the lexical coverage, reduces OOVs to 0.7{\%} and leads to an absolute BLEU improvement of 2.73 points.",
author = "Hassan Sajjad and Kareem Darwish and Yonatan Belinkov",
year = "2013",
month = "1",
day = "1",
language = "English",
isbn = "9781937284510",
volume = "2",
pages = "1--6",
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 - Translating dialectal arabic to english

AU - Sajjad, Hassan

AU - Darwish, Kareem

AU - Belinkov, Yonatan

PY - 2013/1/1

Y1 - 2013/1/1

N2 - We present a dialectal Egyptian Arabic to English statistical machine translation system that leverages dialectal to Modern Standard Arabic (MSA) adaptation. In contrast to previous work, we first narrow down the gap between Egyptian and MSA by applying an automatic characterlevel transformational model that changes Egyptian to EG', which looks similar to MSA. The transformations include morphological, phonological and spelling changes. The transformation reduces the out-of-vocabulary (OOV) words from 5.2% to 2.6% and gives a gain of 1.87 BLEU points. Further, adapting large MSA/English parallel data increases the lexical coverage, reduces OOVs to 0.7% and leads to an absolute BLEU improvement of 2.73 points.

AB - We present a dialectal Egyptian Arabic to English statistical machine translation system that leverages dialectal to Modern Standard Arabic (MSA) adaptation. In contrast to previous work, we first narrow down the gap between Egyptian and MSA by applying an automatic characterlevel transformational model that changes Egyptian to EG', which looks similar to MSA. The transformations include morphological, phonological and spelling changes. The transformation reduces the out-of-vocabulary (OOV) words from 5.2% to 2.6% and gives a gain of 1.87 BLEU points. Further, adapting large MSA/English parallel data increases the lexical coverage, reduces OOVs to 0.7% and leads to an absolute BLEU improvement of 2.73 points.

UR - http://www.scopus.com/inward/record.url?scp=84899950721&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84899950721&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:84899950721

SN - 9781937284510

VL - 2

SP - 1

EP - 6

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

PB - Association for Computational Linguistics (ACL)

ER -