Volume 12, Number 1, September 2016 - DOI: http://dx.doi.org/10.21700/ijcis.2016.273

IJCIS

Computing and Information Sciences is a peer reviewed journal that is committed to timely publication of original research, surveying and tutorial contributions on the analysis and development of computing and information science. The journal is designed mainly to serve researchers and developers, dealing with information and computing. Papers that can provide both theoretical analysis, along with carefully designed computational experiments, are particularly welcome. The journal is published 2-3 times per year with distribution to librarians, universities, research centers, researchers in computing, mathematics, and information science. The journal maintains strict refereeing procedures through its editorial policies in order to publish papers of only the highest quality. The refereeing is done by anonymous Reviewers. Often, reviews take four months to six months to obtain, occasionally longer, and it takes an additional several months for the publication process.

DOI: http://dx.doi.org/10.21700/ijcis.2016.109

Textual Entailment for Arabic Language based on Lexical and Semantic Matching

Mariam Khader*  - email: mkhader@psut.edu.jo 
Arafat Awajan
Akram Alkouz

Department of Computer Science, Princess Sumaya University for Technology, Amman Jordan

*Corresponding author

Received: 1 May 2016
Revised: 10 August 2016
Accepted: 14 September 2016
Published: 29 September 2016

Abstract: Textual Entailment is one of the recent natural language processing challenges, where the meaning of an expression "Hypothesis" could be entailed by the meaning of another expression "Text". In comparison with English Language, the Arabic language has more challenges in determining entailment judgment, due to lexical and syntactic ambiguity. The proposed work in this paper has adopted a lexical analysis technique of Textual Entailment to study the suitability of this technique for Arabic language. In addition a semantic matching approach was added in order to enhance the precision of the proposed entailment system. The lexical analysis is based on calculating word overlap and bigram extraction and matching. The semantic matching has been incorporated with word overlap to increase the accuracy of words matching. The system has been evaluated by measuring precision and recall, those two metrics are the main evaluation measures used in Recognizing Textual Entailmen challenge number 2 to evaluate participated systems. The system has achieved precision of 68%, 58% for both Entails and NotENtails respectively with overall recall of 61%.

Keywords: Textual Entailment; Lexical Analysis; RTE Challenge; Semantic Matching; Arabic Natural Language Processing.


  • PDF (223 KB)
  • ZIP (241 KB)


  •  

    Contacts

    Editor-in-Chief
    Prof. Jihad Mohamad Alja'am 
    Email: journal.editor.ijcis@gmail.com

    The Journal Secretary
    Eng. Dana Bandok
    Ontario, Canada 
    Email: sec.ijcis@gmail.com 

    Home Page »