Abstract
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.
- Mohammed Akour, Sameer Abufardeh, Kenneth Magel, and Qasemm Al-Radaideh. 2011. QArabPro: A rule based question answering system for reading comprehension tests in Arabic. American Journal of Applied Science 8, 6, 652--661.Google ScholarCross Ref
- Fatima Al Kohlani. 2010. The Function of Discourse Markers in Arabic Newspaper Opinion Articles. PhD thesis, Georgetown University, Washington.Google Scholar
- Raffaella Bernardi, Jijkoun Valentin, Mishne Gilad, and De Rijke Maarten. 2003. Selectively using linguistic resources throughout the question answering pipeline. In Proceedings of the 2nd CoLogNET. 50--60.Google Scholar
- Diane Blakemore. 2003. Discourse and relevance theory. In The Handbook of Discourse Analysis. Oxford: Blackwell, 100--115.Google Scholar
- Eric Breck, John Burger, Lisa Ferro, Warren Greiff, Mani Light, and Jason Rennie. 2000. Another sys called Qanda. In Proceedings of the 9th Text REtrieval Conference, NIST Special Publication 500-246. Maryland, 369--379.Google Scholar
- Simon Corston-Oliver. 1998. Computing Representations of the Structure of Written Discourse. PhD thesis, University of California, Santa Barbara. Google ScholarDigital Library
- Shehdeh Fareh and Jihad Hamdan. 1999. The translation of arabic ‘wa’ into English: Some problems and implications. In Dirasat: Human and Social Science, 26, 590--603.Google Scholar
- Vanessa Feng and Graeme Hirst. 2012. Text-level discourse parsing with rich linguistic features. In Proceedings of the 50th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies (ACL’12). Google ScholarDigital Library
- Bruce Fraser. 1996. Pragmatic markers. Pragmatics 6, 2, 167--190.Google ScholarCross Ref
- Ryuichiro Higashinaka and Hideki Isozaki. 2008. Corpus-based question answering for why-question. In Proceedings of the 3rd International Joint Conference on Natural Language Processing. 1, 418--425.Google Scholar
- Ahmed Ibrahim and Tarek Elghazaly. 2012. Arabic text summarization using rhetorical structure theory. In 8th International Conference on Informatics and Systems (INFOS’12). IEEE, 34--38.Google Scholar
- Julian Kupice. 1999. MURAX: Finding and organizing answers form text search. Natural Language Information Retrieval. Netherlands, 311--332.Google Scholar
- William Mann and Sandra Thompson. 1988. A rhetorical structure theory: Toward a functional theory of text organization. Text-Interdisciplinary Journal for the study of Discourse 8, 3, 243--281.Google Scholar
- Daniel Marcu. 2000a. The rhetorical parsing of unrestricted texts: A surface-based approach. Computational Linguistics 26, 3, 395--448. Google ScholarDigital Library
- Daniel Marcu. 2000b. The Theory and Practice of Discourse Parsing and Summarization. MIT Press, London. Google ScholarDigital Library
- Hassan Mathkour, Ameur Touir, and Waleed Al-Sanea. 2008. Parsing arabic texts using rhetorical structure theory. Journal of Computer Science 4, 9, 713--720.Google ScholarCross Ref
- Jawad Sadek and Farid Meziane. 2016. Extracting arabic causal relations using linguistic patterns. Journal ACM Translations on Asian and Low-Resource Language Information Processing 15, 3, Article 14. Google ScholarDigital Library
- Jawad Sadek. 2013. Automatic detection of Arabic causal relations. In Proceedings of the 18th International Conference on Application of Natural Language to Information Systems (NLDB’13). UK, 400--403.Google ScholarCross Ref
- Jawad Sadek, Fairouz Chakkour, and Farid Meziane. 2012. Arabic rhetorical relations extraction for answering “why” and “how to” questions. In Proceedings of the 17th International Conference on Application of Natural Language to Information Systems (NLDB’12). The Netherlands, 385--390. Google ScholarDigital Library
- Ted Sanders and Leo Noordman. 2000. The role of coherence relations and their linguistic markers in text processing. Discourse Processes 29, 1, 37--60.Google ScholarCross Ref
- Deborah Schiffrin, Deborah Tannen, and Heidi Hamilton. 2001. Discourse Markers: Language, Meaning, and Context. Basil Blackwell, Oxford.Google Scholar
- Bernard Schneuwly. 1997. Textual organizers and text types: Ontogenetic aspects in writing. Processing Interclausal Relationships: Studies in the Production and Comprehension of Text, 245--263.Google Scholar
- Erwin Segal, Judith Duchan, and Paula Scott. 1991. The role of interclausal connectives in narrative structuring: Evidence from adults’ interpretation of simple stories. Discourse Processes 14, 27--54.Google ScholarCross Ref
- Hideki Shima and Teruko Mitamura. 2007. JAVELIN III: Answering non-factoid question in Japanese. In Proceedings of NTCIR-6 Workshop Meeting. Tokyo, 464--468.Google Scholar
- Radu Soricut and Daniel Marcu. 2003. Sentence level discourse parsing using syntactic and lexical information. In Proceedings of the Human Language Technology and North American Association for Computational Linguistics. Canada, 149--156. Google ScholarDigital Library
- Mihai Surdeanu, Massimiliano Giaramita, and Hugo Zaragoza. 2008. Learning to rank answers on large online qa collections. In Proceedings of ACL’08. 719--727.Google Scholar
- Daphne Theijssen. 2007. Feature for Automatic Discourse Analysis of Paragraphs. Master's thesis. Radboud Universiteit Nijmegen, The Netherlands.Google Scholar
- Sander Timmerman. 2007. Automatic Recognition of Structural Relations in Dutch Text. Master's thesis. University of Twente, The Netherlands.Google Scholar
- Suzan Verberne. 2007. Paragraph retrieval for why-question answering. In Proceedings of the 30th Annual International ACMSIGR Conference on Research and Development in Information Retrieval. New York, 922--927. Google ScholarDigital Library
- Suzan Verberne, Lou Boves, and Nelleke Osstdijk. 2007. Discourse-based answering of why-questions. Traitement Automatique Des Langues, Special Issue on Computational Approaches to Discourse and Document Processing 47, 2, 21--41.Google Scholar
- William Wright and Paul Caspari. 1896. A Grammar of the Arabic Language. Cambridge University Press, UK.Google Scholar
- Mai Zaki 2011. The Semantics and Pragmatics of Demonstratives in English and Arabic. PhD thesis, University of Middlesex.Google Scholar
Index Terms
- A Discourse-Based Approach for Arabic Question Answering
Recommendations
A Survey of Discourse Representations for Chinese Discourse Annotation
A key element in computational discourse analysis is the design of a formal representation for the discourse structure of a text. With machine learning being the dominant method, it is important to identify a discourse representation that can be used to ...
An xpath-based discourse analysis module for spoken dialogue systems
WWW Alt. '04: Proceedings of the 13th international World Wide Web conference on Alternate track papers & postersThis paper describes an XPath-based discourse analysis module for Spoken Dialogue Systems that allows the dialogue author to easily manipulate and query both the user input's semantic representation and the dialogue context using a simple and compact ...
Arabic rhetorical relations extraction for answering "why" and "how to" questions
NLDB'12: Proceedings of the 17th international conference on Applications of Natural Language Processing and Information SystemsIn the current study we aim at exploiting discourse structure of Arabic text to automatically finding answers to non-factoid questions ("Why" and "How to"). Our method is based on Rhetorical Structure Theory (RST) that many studies have shown to be a ...
Comments