Processing Judeo-Arabic texts

Kfir Bar; Nachum Dershowitz; Lior Wolf; Yackov Lubarsky; Yaacov Choueka

doi:10.1109/acling.2015.27

Processing Judeo-Arabic texts

Kfir Bar, Nachum Dershowitz, Lior Wolf, Yackov Lubarsky, Yaacov Choueka

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

3 Scopus citations

Abstract

Judeo-Arabic is a set of dialects spoken and written by Jewish communities living in Arab countries. Judeo-Arabic is typically written in Hebrew letters, enriched with diacritic marks that relate to the underlying Arabic. However, some inconsistencies in rendering words in Hebrew letters increase the level of ambiguity of a given word. Furthermore, Judeo-Arabic texts usually contain non-Arabic words and phrases, such as quotations or borrowed words from Hebrew and Aramaic. We focus on two main tasks: (1) automatic transliteration of Judeo-Arabic Hebrew letters into Arabic letters, and (2) automatic identification of language switching points between Judeo-Arabic and Hebrew. For transliteration, we employ a statistical translation system trained on the character level, resulting in 96.9% precision, a significant improvement over the baseline. For the language switching task, we use a word-level supervised classifier, also showing some significant improvements over the baseline.

Original language	English
Title of host publication	Proceedings - 1st International Conference on Arabic Computational Linguistics
Subtitle of host publication	Advances in Arabic Computational Linguistics, ACLing 2015
Editors	Alexander Gelbukh, Khaled Shaalan
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	138-144
Number of pages	7
ISBN (Electronic)	9781467391559
DOIs	https://doi.org/10.1109/acling.2015.27
State	Published - 29 Feb 2016
Externally published	Yes
Event	1st International Conference on Arabic Computational Linguistics, ACLing 2015 - Cairo, Egypt Duration: 17 Apr 2015 → 20 Apr 2015

Publication series

Name	Proceedings - 1st International Conference on Arabic Computational Linguistics: Advances in Arabic Computational Linguistics, ACLing 2015

Conference

Conference	1st International Conference on Arabic Computational Linguistics, ACLing 2015
Country/Territory	Egypt
City	Cairo
Period	17/04/15 → 20/04/15

Bibliographical note

Publisher Copyright:
© 2015 IEEE.

Funding

We would like to thank the anonymous reviewers for their helpful suggestions and comments.

Keywords

Code switching
Judeo-Arabic
Transliteration

Access to Document

10.1109/acling.2015.27

Cite this

Bar, K., Dershowitz, N., Wolf, L., Lubarsky, Y., & Choueka, Y. (2016). Processing Judeo-Arabic texts. In A. Gelbukh, & K. Shaalan (Eds.), Proceedings - 1st International Conference on Arabic Computational Linguistics: Advances in Arabic Computational Linguistics, ACLing 2015 (pp. 138-144). Article 7422292 (Proceedings - 1st International Conference on Arabic Computational Linguistics: Advances in Arabic Computational Linguistics, ACLing 2015). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/acling.2015.27

Bar, Kfir ; Dershowitz, Nachum ; Wolf, Lior et al. / Processing Judeo-Arabic texts. Proceedings - 1st International Conference on Arabic Computational Linguistics: Advances in Arabic Computational Linguistics, ACLing 2015. editor / Alexander Gelbukh ; Khaled Shaalan. Institute of Electrical and Electronics Engineers Inc., 2016. pp. 138-144 (Proceedings - 1st International Conference on Arabic Computational Linguistics: Advances in Arabic Computational Linguistics, ACLing 2015).

@inproceedings{b167d52bc896436c9533aeb338442767,

title = "Processing Judeo-Arabic texts",

abstract = "Judeo-Arabic is a set of dialects spoken and written by Jewish communities living in Arab countries. Judeo-Arabic is typically written in Hebrew letters, enriched with diacritic marks that relate to the underlying Arabic. However, some inconsistencies in rendering words in Hebrew letters increase the level of ambiguity of a given word. Furthermore, Judeo-Arabic texts usually contain non-Arabic words and phrases, such as quotations or borrowed words from Hebrew and Aramaic. We focus on two main tasks: (1) automatic transliteration of Judeo-Arabic Hebrew letters into Arabic letters, and (2) automatic identification of language switching points between Judeo-Arabic and Hebrew. For transliteration, we employ a statistical translation system trained on the character level, resulting in 96.9% precision, a significant improvement over the baseline. For the language switching task, we use a word-level supervised classifier, also showing some significant improvements over the baseline.",

keywords = "Code switching, Judeo-Arabic, Transliteration",

author = "Kfir Bar and Nachum Dershowitz and Lior Wolf and Yackov Lubarsky and Yaacov Choueka",

note = "Publisher Copyright: {\textcopyright} 2015 IEEE.; 1st International Conference on Arabic Computational Linguistics, ACLing 2015 ; Conference date: 17-04-2015 Through 20-04-2015",

year = "2016",

month = feb,

day = "29",

doi = "10.1109/acling.2015.27",

language = "אנגלית",

series = "Proceedings - 1st International Conference on Arabic Computational Linguistics: Advances in Arabic Computational Linguistics, ACLing 2015",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "138--144",

editor = "Alexander Gelbukh and Khaled Shaalan",

booktitle = "Proceedings - 1st International Conference on Arabic Computational Linguistics",

address = "ארצות הברית",

}

Bar, K, Dershowitz, N, Wolf, L, Lubarsky, Y & Choueka, Y 2016, Processing Judeo-Arabic texts. in A Gelbukh & K Shaalan (eds), Proceedings - 1st International Conference on Arabic Computational Linguistics: Advances in Arabic Computational Linguistics, ACLing 2015., 7422292, Proceedings - 1st International Conference on Arabic Computational Linguistics: Advances in Arabic Computational Linguistics, ACLing 2015, Institute of Electrical and Electronics Engineers Inc., pp. 138-144, 1st International Conference on Arabic Computational Linguistics, ACLing 2015, Cairo, Egypt, 17/04/15. https://doi.org/10.1109/acling.2015.27

Processing Judeo-Arabic texts. / Bar, Kfir; Dershowitz, Nachum; Wolf, Lior et al.
Proceedings - 1st International Conference on Arabic Computational Linguistics: Advances in Arabic Computational Linguistics, ACLing 2015. ed. / Alexander Gelbukh; Khaled Shaalan. Institute of Electrical and Electronics Engineers Inc., 2016. p. 138-144 7422292 (Proceedings - 1st International Conference on Arabic Computational Linguistics: Advances in Arabic Computational Linguistics, ACLing 2015).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Processing Judeo-Arabic texts

AU - Bar, Kfir

AU - Dershowitz, Nachum

AU - Wolf, Lior

AU - Lubarsky, Yackov

AU - Choueka, Yaacov

PY - 2016/2/29

Y1 - 2016/2/29

N2 - Judeo-Arabic is a set of dialects spoken and written by Jewish communities living in Arab countries. Judeo-Arabic is typically written in Hebrew letters, enriched with diacritic marks that relate to the underlying Arabic. However, some inconsistencies in rendering words in Hebrew letters increase the level of ambiguity of a given word. Furthermore, Judeo-Arabic texts usually contain non-Arabic words and phrases, such as quotations or borrowed words from Hebrew and Aramaic. We focus on two main tasks: (1) automatic transliteration of Judeo-Arabic Hebrew letters into Arabic letters, and (2) automatic identification of language switching points between Judeo-Arabic and Hebrew. For transliteration, we employ a statistical translation system trained on the character level, resulting in 96.9% precision, a significant improvement over the baseline. For the language switching task, we use a word-level supervised classifier, also showing some significant improvements over the baseline.

AB - Judeo-Arabic is a set of dialects spoken and written by Jewish communities living in Arab countries. Judeo-Arabic is typically written in Hebrew letters, enriched with diacritic marks that relate to the underlying Arabic. However, some inconsistencies in rendering words in Hebrew letters increase the level of ambiguity of a given word. Furthermore, Judeo-Arabic texts usually contain non-Arabic words and phrases, such as quotations or borrowed words from Hebrew and Aramaic. We focus on two main tasks: (1) automatic transliteration of Judeo-Arabic Hebrew letters into Arabic letters, and (2) automatic identification of language switching points between Judeo-Arabic and Hebrew. For transliteration, we employ a statistical translation system trained on the character level, resulting in 96.9% precision, a significant improvement over the baseline. For the language switching task, we use a word-level supervised classifier, also showing some significant improvements over the baseline.

KW - Code switching

KW - Judeo-Arabic

KW - Transliteration

UR - http://www.scopus.com/inward/record.url?scp=84969799380&partnerID=8YFLogxK

U2 - 10.1109/acling.2015.27

DO - 10.1109/acling.2015.27

M3 - ???researchoutput.researchoutputtypes.contributiontobookanthology.conference???

AN - SCOPUS:84969799380

T3 - Proceedings - 1st International Conference on Arabic Computational Linguistics: Advances in Arabic Computational Linguistics, ACLing 2015

SP - 138

EP - 144

BT - Proceedings - 1st International Conference on Arabic Computational Linguistics

A2 - Gelbukh, Alexander

A2 - Shaalan, Khaled

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 1st International Conference on Arabic Computational Linguistics, ACLing 2015

Y2 - 17 April 2015 through 20 April 2015

ER -

Bar K, Dershowitz N, Wolf L, Lubarsky Y, Choueka Y. Processing Judeo-Arabic texts. In Gelbukh A, Shaalan K, editors, Proceedings - 1st International Conference on Arabic Computational Linguistics: Advances in Arabic Computational Linguistics, ACLing 2015. Institute of Electrical and Electronics Engineers Inc. 2016. p. 138-144. 7422292. (Proceedings - 1st International Conference on Arabic Computational Linguistics: Advances in Arabic Computational Linguistics, ACLing 2015). doi: 10.1109/acling.2015.27

Processing Judeo-Arabic texts

Abstract

Publication series

Conference

Bibliographical note

Funding

Keywords

Access to Document

Other files and links

Fingerprint

Cite this