A Chatbot as a Natural Web Interface to Arabic Web QA

In this paper, we describe a way to access Arabic Web Question Answering (QA) corpus using a chatbot, without the need for sophisticated natural language processing or logical inference. Any Natural Language (NL) interface to Question Answer (QA) system is constrained to reply with the given answers, so there is no need for NL generation to recreate well-formed answers, or for deep analysis or logical inference to map user input questions onto this logical ontology; simple (but large) set of pattern-template matching rules will suffice. In previous research, this approach works properly with English and other European languages. In this paper, we try to see how the same chatbot will react in terms of Arabic Web QA corpus. Initial results shows that 93% of answers were correct, but because of a lot of characteristics related to Arabic language, changing Arabic questions into other forms may lead to no answers.

[1]  Haidar Moukdad.  Lost in Cyberspace: How Do Search Engines Handle Arabic Queries? , 2013 .

[2]  Ghassan Kanaan,et al.  A New Question Answering System for the Arabic Language , 2009 .

[3]  Nasredine Semmar,et al.  Arabic to French Sentence Alignment: Exploration of A Cross-language Information Retrieval Approach , 2007, SEMITIC@ACL.

[4]  K. M. Colby,et al.  Human-Computer Conversation in A Cognitive Therapy Program , 1999 .

[5]  C. Fellbaum,et al.  Arabic WordNet and the Challenges of Arabic , 2006, BCS.

[6]  Paolo Rosso,et al.  Arabic-English Question Answering , 2005 .

[7]  Ahmed Abdelali,et al.  Arabic Information Retrieval Perspectives , 2004 .

[8]  Elizabeth D. Liddy,et al.  Analyst-Focused Arabic Information Retrieval , 2005 .

[9]  Jimmy J. Lin,et al.  Omnibase: Uniform Access to Heterogeneous Data for Question Answering , 2002, NLDB.

[10]  Ophir Frieder,et al.  On Arabic-English cross-language information retrieval: a machine translation approach , 2002, Proceedings. International Conference on Information Technology: Coding and Computing.

[11]  Andrew Roberts,et al.  FAQchat as in Information Retrieval system , 2005 .

[12]  Mohammad Reza Kangavari,et al.  A New Model for Question Answering Systems , 2008 .

[13]  Alexander M. Fraser,et al.  Empirical studies in strategies for Arabic retrieval , 2002, SIGIR '02.

[14]  Bassam H. Hammo.  Towards enhancing retrieval effectiveness of search engines for diacritisized Arabic documents , 2008, Information Retrieval.

[15]  Jimmy J. Lin,et al.  Web question answering: is more always better? , 2002, SIGIR '02.

[16]  Dell Zhang,et al.  A Web-based Question Answering System , 2003 .

[17]  Wen-Lian Hsu,et al.  An alignment-based surface pattern for a question answering system , 2008, 2008 IEEE International Conference on Information Reuse and Integration.

[18]  S. Khoja,et al.  APT: Arabic Part-of-speech Tagger , 2001 .

[19]  Lisa Ballesteros,et al.  Improving stemming for Arabic information retrieval: light stemming and co-occurrence analysis , 2002, SIGIR '02.

[20]  Mona T. Diab.  Improved Arabic Base Phrase Chunking with a new enriched POS tag set , 2007, SEMITIC@ACL.

[21]  Nasredine Semmar,et al.  Using Stemming in Morphological Analysis to Improve Arabic Information Retrieval , 2006, JEPTALNRECITAL.

[22]  Eric Atwell,et al.  An Arabic chatbot giving answers from the Qur'an , 2004 .

[23]  F. A. Mohammed,et al.  A knowledge based Arabic question answering system (AQAS) , 1993, SGAR.

[24]  Leah S. Larkey,et al.  Statistical transliteration for english-arabic cross language information retrieval , 2003, CIKM '03.

[25]  D. Graddol.  The Future of English , 2018, The Emergence and Development of English.

[26]  Joseph Weizenbaum,et al.  and Machine , 1977 .