Arabic retrieval revisited: Morphological hole filling

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

8 Citations (Scopus)

Abstract

Due to Arabic's morphological complexity, Arabic retrieval benefits greatly from morphological analysis - particularly stemming. However, the best known stemming does not handle linguistic phenomena such as broken plurals and malformed stems. In this paper we propose a model of character-level morphological transformation that is trained using Wikipedia hypertext to page title links. The use of our model yields statistically significant improvements in Arabic retrieval over the use of the best statistical stemming technique. The technique can potentially be applied to other languages.

Original languageEnglish
Title of host publication50th Annual Meeting of the Association for Computational Linguistics, ACL 2012 - Proceedings of the Conference
Pages218-222
Number of pages5
Volume2
Publication statusPublished - 1 Dec 2012
Event50th Annual Meeting of the Association for Computational Linguistics, ACL 2012 - Jeju Island, Korea, Republic of
Duration: 8 Jul 201214 Jul 2012

Other

Other50th Annual Meeting of the Association for Computational Linguistics, ACL 2012
CountryKorea, Republic of
CityJeju Island
Period8/7/1214/7/12

Fingerprint

Linguistics

ASJC Scopus subject areas

  • Computational Theory and Mathematics
  • Software

Cite this

Darwish, K., & Ali, A. (2012). Arabic retrieval revisited: Morphological hole filling. In 50th Annual Meeting of the Association for Computational Linguistics, ACL 2012 - Proceedings of the Conference (Vol. 2, pp. 218-222)

Arabic retrieval revisited : Morphological hole filling. / Darwish, Kareem; Ali, Ahmed.

50th Annual Meeting of the Association for Computational Linguistics, ACL 2012 - Proceedings of the Conference. Vol. 2 2012. p. 218-222.

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

Darwish, K & Ali, A 2012, Arabic retrieval revisited: Morphological hole filling. in 50th Annual Meeting of the Association for Computational Linguistics, ACL 2012 - Proceedings of the Conference. vol. 2, pp. 218-222, 50th Annual Meeting of the Association for Computational Linguistics, ACL 2012, Jeju Island, Korea, Republic of, 8/7/12.
Darwish K, Ali A. Arabic retrieval revisited: Morphological hole filling. In 50th Annual Meeting of the Association for Computational Linguistics, ACL 2012 - Proceedings of the Conference. Vol. 2. 2012. p. 218-222
Darwish, Kareem ; Ali, Ahmed. / Arabic retrieval revisited : Morphological hole filling. 50th Annual Meeting of the Association for Computational Linguistics, ACL 2012 - Proceedings of the Conference. Vol. 2 2012. pp. 218-222
@inproceedings{80acbbb337354a55961bdcbecee3c365,
title = "Arabic retrieval revisited: Morphological hole filling",
abstract = "Due to Arabic's morphological complexity, Arabic retrieval benefits greatly from morphological analysis - particularly stemming. However, the best known stemming does not handle linguistic phenomena such as broken plurals and malformed stems. In this paper we propose a model of character-level morphological transformation that is trained using Wikipedia hypertext to page title links. The use of our model yields statistically significant improvements in Arabic retrieval over the use of the best statistical stemming technique. The technique can potentially be applied to other languages.",
author = "Kareem Darwish and Ahmed Ali",
year = "2012",
month = "12",
day = "1",
language = "English",
isbn = "9781937284251",
volume = "2",
pages = "218--222",
booktitle = "50th Annual Meeting of the Association for Computational Linguistics, ACL 2012 - Proceedings of the Conference",

}

TY - GEN

T1 - Arabic retrieval revisited

T2 - Morphological hole filling

AU - Darwish, Kareem

AU - Ali, Ahmed

PY - 2012/12/1

Y1 - 2012/12/1

N2 - Due to Arabic's morphological complexity, Arabic retrieval benefits greatly from morphological analysis - particularly stemming. However, the best known stemming does not handle linguistic phenomena such as broken plurals and malformed stems. In this paper we propose a model of character-level morphological transformation that is trained using Wikipedia hypertext to page title links. The use of our model yields statistically significant improvements in Arabic retrieval over the use of the best statistical stemming technique. The technique can potentially be applied to other languages.

AB - Due to Arabic's morphological complexity, Arabic retrieval benefits greatly from morphological analysis - particularly stemming. However, the best known stemming does not handle linguistic phenomena such as broken plurals and malformed stems. In this paper we propose a model of character-level morphological transformation that is trained using Wikipedia hypertext to page title links. The use of our model yields statistically significant improvements in Arabic retrieval over the use of the best statistical stemming technique. The technique can potentially be applied to other languages.

UR - http://www.scopus.com/inward/record.url?scp=84878206852&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84878206852&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:84878206852

SN - 9781937284251

VL - 2

SP - 218

EP - 222

BT - 50th Annual Meeting of the Association for Computational Linguistics, ACL 2012 - Proceedings of the Conference

ER -