A Discourse-Based Approach for Arabic Question Answering

The treatment of complex questions with explanatory answers involves searching for arguments in texts. Because of the prominent role that discourse relations play in reflecting text producers’ intentions, capturing the underlying structure of text constitutes a good instructor in this issue. From our extensive review, a system for automatic discourse analysis that creates full rhetorical structures in large-scale Arabic texts is currently unavailable. This is due to the high computational complexity involved in processing a large number of hypothesized relations associated with large texts. Therefore, more practical approaches should be investigated. This article presents a new Arabic Text Parser oriented for question-answering systems dealing with لماذا “why” and كيف “how to” questions. The Text Parser presented here considers the sentence as the basic unit of text and incorporates a set of heuristics to avoid computational explosion. With this approach, the developed question-answering system reached a significant improvement over the baseline with a Recall of 68% and MRR of 0.62.

[1]  Julian M. Kupiec.  Murax: Finding and Organizing Answers from Text Search , 1999 .

[2]  Farid Meziane,et al.  Arabic Rhetorical Relations Extraction for Answering "Why" and "How to" Questions , 2012, NLDB.

[3]  Suzan Verberne.  Paragraph retrieval for why-question answering , 2007, SIGIR.

[4]  A. Ibrahim,et al.  Arabic text summarization using Rhetorical Structure Theory , 2012, 2012 8th International Conference on Informatics and Systems (INFOS).

[5]  William C. Mann,et al.  Rhetorical Structure Theory: Toward a functional theory of text organization , 1988 .

[6]  Yael Maschler,et al.  Discourse Markers: Language, Meaning, and Context , 2005 .

[7]  Kenneth Magel,et al.  QArabPro: A Rule Based Question Answering System for Reading Comprehension Tests in Arabic , 2011 .

[8]  B. Schneuwly,et al.  Textual Organizers and Text Types: Ontogenetic Aspects in Writing , 1997 .

[9]  Gilad Mishne,et al.  Selectively using linguistic resources throughout the question answering pipeline , 2003 .

[10]  Lou Boves,et al.  Discourse-based answering of why-questions , 2006, Trait. Autom. des Langues.

[11]  Hassan Mathkour,et al.  Parsing Arabic Texts Using Rhetorical Structure Theory , 2008 .

[12]  Mihai Surdeanu,et al.  Learning to Rank Answers on Large Online QA Collections , 2008, ACL.

[13]  E. M. Segal,et al.  The role of interclausal connectives in narrative structuring: Evidence from adults' interpretations of simple stories , 1991 .

[14]  Michel Fayol,et al.  Processing interclausal relationships : studies in the production and comprehension of text , 1997 .

[15]  Farid Meziane,et al.  Extracting Arabic Causal Relations Using Linguistic Patterns , 2016, ACM Trans. Asian Low Resour. Lang. Inf. Process..

[16]  Teruko Mitamura,et al.  JAVELIN III: Answering Non-Factoid Questions in Japanese , 2007, NTCIR.

[17]  Graeme Hirst,et al.  Text-level Discourse Parsing with Rich Linguistic Features , 2012, ACL.

[18]  S. Corston-Oliver,et al.  Computing representations of the structure of written discourse , 1998 .

[19]  Daniel Marcu,et al.  Sentence Level Discourse Parsing using Syntactic and Lexical Information , 2003, NAACL.

[20]  Daniel Marcu,et al.  The rhetorical parsing of unrestricted texts: a surface-based approach , 2000, CL.

[21]  Edward Henry Palmer.  A Grammar of the Arabic Language , 2004 .

[22]  Al Kohlani,et al.  The function of discourse markers in Arabic newspaper opinion articles , 2010 .

[23]  Inderjeet Mani,et al.  Another Sys Called Qanda , 2000, TREC.

[24]  Ted Sanders,et al.  The Role of Coherence Relations and Their Linguistic Markers in Text Processing , 2000 .

[25]  Diane Blakemore,et al.  Discourse and Relevance Theory , 2005 .

[26]  Jawad Sadek.  Automatic Detection of Arabic Causal Relations , 2013, NLDB.

[27]  Duncan Forbes,et al.  Grammar of the arabic language , 2011 .

[28]  Ryuichiro Higashinaka,et al.  Corpus-based Question Answering for why-Questions , 2008, IJCNLP.

[29]  Lou Boves,et al.  Features for automatic discourse analysis of paragraphs , 2008 .