Not all the questions are (equally) difficult. An hybrid approach to CQA in Arabic

In the past we faced the problem of Community Question Answering using an unified approach. Some of the questions, however, are easier to be approached by a conventional rule-based system. In this paper we explore this direction.

[1]  Preslav Nakov,et al.  SemEval-2017 Task 3: Community Question Answering , 2017, *SEMEVAL.

[2]  Paolo Rosso,et al.  DefArabicQA: Arabic Definition Question Answering System , 2010 .

[3]  Fatima T. AL-Khawaldeh.  Answer Extraction for Why Arabic Questions Answering Systems: EWAQ , 2019, ArXiv.

[4]  Quoc V. Le,et al.  Distributed Representations of Sentences and Documents , 2014, ICML.

[5]  Francis R. Bach,et al.  Online Learning for Latent Dirichlet Allocation , 2010, NIPS.

[6]  Wael Hassan Gomaa,et al.  A Survey of Text Similarity Approaches , 2013 .

[7]  Mihai Surdeanu,et al.  The Stanford CoreNLP Natural Language Processing Toolkit , 2014, ACL.

[8]  Horacio Rodríguez,et al.  UPC-USMBA at SemEval-2017 Task 3: Combining multiple approaches for CQA for Arabic , 2017, SemEval@ACL.

[9]  Yassine Benajiba.  Arabic Named Entity Recognition , 2010, Proces. del Leng. Natural.

[10]  Mariano Felice,et al.  Linguistic Indicators for Quality Estimation of Machine Translations , 2012 .

[11]  Christiane Fellbaum,et al.  Book Reviews: WordNet: An Electronic Lexical Database , 1999, CL.

[12]  Horacio Rodríguez,et al.  Arabic medical entity tagging using distant learning in a Multilingual Framework , 2017, J. King Saud Univ. Comput. Inf. Sci..

[13]  Christiane Fellbaum,et al.  Arabic WordNet. Current State and Future Extensions , 2008 .

[14]  Horacio Rodríguez,et al.  Using domain knowledge and bilingual resources for addressing community question answering for Arabic , 2016, 2016 4th IEEE International Colloquium on Information Science and Technology (CiSt).