Ambiguous Arabic Words Disambiguation

Author

Merhbene, Laroussi ; Zouaghi, Anis ; Zrigu, Mounir

Author_Institution

Fac. of Sci. of Monastir, UTIC, Monastir, Tunisia

fYear

2010

fDate

9-11 June 2010

Firstpage

157

Lastpage

164

Abstract

In this paper we put forward an unsupervised system WSD-AL for Arabic word disambiguation. We apply some pre-processing steps to texts containing the ambiguous word in the corpus and we extract the most relevant words. Then, we put to use the Context-Matching algorithm that returns a semantic coherence score corresponding to the context of use that is semantically closest to the original sentence. These Contexts are generated using the glosses of the ambiguous word and the corpus. The results found by the proposed system are satisfactory, as the rate of disambiguation obtained equals 78.

Keywords

natural language processing; pattern matching; unsupervised learning; ambiguous Arabic words disambiguation; context-matching algorithm; unsupervised system WSD-AL; Artificial intelligence; Clustering algorithms; Databases; Dictionaries; Distributed computing; Handicapped aids; Software engineering; Speech recognition; Testing; Thesauri; Context of uses; Context-Matching algorithm; Pre-processing; glosses;

fLanguage

English

Publisher

ieee

Conference_Titel

Software Engineering Artificial Intelligence Networking and Parallel/Distributed Computing (SNPD), 2010 11th ACIS International Conference on

Conference_Location

London

Print_ISBN

978-1-4244-7422-6

Electronic_ISBN

978-1-4244-7421-9

Type

conf

DOI

10.1109/SNPD.2010.32

Filename

5521518