Contribution to Semantic Analysis of Arabic Language

Anis Zouaghi,Laroussi Merhbene,Mounir Zrigui,Georges Antoniadis

doi:10.1155/2012/620461

Abstract

We propose a new approach for determining the adequate sense of Arabic words. For that, we propose an algorithm based on information retrieval measures to identify the context of use that is the closest to the sentence containing the word to be disambiguated. The contexts of use represent a set of sentences that indicates a particular sense of the ambiguous word. These contexts are generated using the words that define the senses of the ambiguous words, the exact string-matching algorithm, and the corpus. We use the measures employed in the domain of information retrieval, Harman, Croft, and Okapi combined to the Lesk algorithm, to assign the correct sense of those proposed.

Highlights

Human language is ambiguous; many words can have more than one sense: this sense is dependent on the context of use
We apply the measures of Harman [6], Croft [7], and Okapi [8] that compares the original sentence with the generated contexts of use and returns a score that corresponds to the closest context of use [9]
We propose some measure that determines the degree of similarity between a sentence and a document

Summary

Introduction

Human language is ambiguous; many words can have more than one sense: this sense is dependent on the context of use. We are interested in determining the meaning of Arabic ambiguous words which we can meet in the messages transcribed by the module of speech recognition. We use a predefined list of stopwords (which do not affect the meaning of the ambiguous words) to eliminate them from the original sentence containing the ambiguous word. We apply the measures of Harman [6], Croft [7], and Okapi [8] that compares the original sentence with the generated contexts of use and returns a score that corresponds to the closest context of use [9]. The Lesk algorithm [10] will be used to choose the exact sense from the different senses given by these measures

Methods

Results

Conclusion