Recognizing Textual Entailment for Arabic using semantic similarity and Word Sense Disambiguation

In this paper, we propose a semantic method for recognizing textual entailment in Arabic. The proposed method serves to detect the directional semantic entailment relationship between text/hypothesis pairs. More specifically, we work at the sentence level, conducting semantic similarity measure and word sense disambiguation process in order to detect entailment relationship in the context of Arabic question/answering system. The results obtained are encouraging. Our method has reached an accuracy of 70%.

[1]  M. Marelli,et al.  SemEval-2014 Task 1: Evaluation of Compositional Distributional Semantic Models on Full Sentences through Semantic Relatedness and Textual Entailment , 2014, *SEMEVAL.

[2]  Mahmoud Neji,et al.  AQA-WebCorp: Web-based Factual Questions for Arabic , 2016, KES.

[3]  Allen H. Renear,et al.  Defining textual entailment , 2018, J. Assoc. Inf. Sci. Technol..

[4]  Mona T. Diab,et al.  Arabic Textual Entailment with Word Embeddings , 2017, WANLP@EACL.

[5]  Christiane Fellbaum,et al.  Introducing the Arabic WordNet project , 2006 .

[6]  Martha Palmer,et al.  Verb Semantics and Lexical Selection , 1994, ACL.

[7]  El Habib Ben Lahmar,et al.  Word Sense Disambiguation Approach for Arabic Text , 2016 .

[8]  Maytham Alabbas,et al.  A Dataset for Arabic Textual Entailment , 2013, RANLP.

[9]  Fatima T. AL-Khawaldeh.  A Study of the Effect of Resolving Negation and Sentiment Analysis in Recognizing Text Entailment for Arabic , 2019, ArXiv.

[10]  Samuel R. Bowman,et al.  The RepEval 2017 Shared Task: Multi-Genre Natural Language Inference with Sentence Representations , 2017, RepEval@EMNLP.

[11]  Maytham Alabbas.  ArbTE: Arabic Textual Entailment , 2011, RANLP Student Research Workshop.

[12]  Alexander F. Gelbukh,et al.  Semantic Textual Similarity Methods, Tools, and Applications: A Survey , 2016, Computación y Sistemas.

[13]  Allan Ramsay,et al.  Natural Language Inference for Arabic Using Extended Tree Edit Distance with Subtrees , 2013, J. Artif. Intell. Res..

[14]  Nababteh Mohammed,et al.  Experimental Study of Semantic Similarity Measures on Arabic WordNet , 2017 .

[15]  Leah S. Larkey,et al.  Arabic Information Retrieval at UMass in TREC-10 , 2001, TREC.

[16]  Lingling Meng,et al.  A New Method for Calculating Word Sense Similarity in WordNet1 , 2012 .

[17]  Zhen-Hua Ling,et al.  Neural Natural Language Inference Models Enhanced with External Knowledge , 2017, ACL.

[18]  Adam Kilgarriff,et al.  Framework and Results for English SENSEVAL , 2000, Comput. Humanit..

[19]  Bilel Elayeb,et al.  Arabic word sense disambiguation: a review , 2019, Artificial Intelligence Review.

[20]  Arafat Awajan,et al.  Textual Entailment for Arabic Language based on Lexical and Semantic Matching , 2016 .

[21]  Henrique Lopes Cardoso,et al.  Recognizing Textual Entailment: Challenges in the Portuguese Language , 2018, Inf..

[22]  Ted Pedersen,et al.  WordNet::Similarity - Measuring the Relatedness of Concepts , 2004, NAACL.

[23]  Mahmoud Neji,et al.  An Arabic Question-Answering System Combining a Semantic and Logical Representation of Texts , 2017, ISDA.