Abstract
This paper explores a suitable way to integrate a Textual Entailment (TE) system, which detects unidirectional semantic inferences, into Question Answering (QA) tasks. We propose using TE as an answer validation engine to improve QA systems, and we evaluate its performance using the Answer Validation Exercise framework. Results point out that our TE system can improve the QA task considerably.
This research has been partially subsidized by the Spanish Government under project TIN2006-15265-C06-01 and by the QALL-ME consortium, 6th Framework Research Programme of the European Union (EU), FP6-IST-033860.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsReferences
Giampiccolo, D., Magnini, B., Dagan, I., Dolan, B.: The Third PASCAL Recognizing Textual Entailment Challenge. In: Proceedings of the ACL-PASCAL Workshop on Textual Entailment and Paraphrasing, Prague, June 2007, pp. 1–9 (2007)
Ferrández, O., Micol, D., Muñoz, R., Palomar, M.: A Perspective-Based Approach for Solving Textual Entailment Recognition. In: Proceedings of the ACL-PASCAL Workshop on Textual Entailment and Paraphrasing, Prague, June 2007, pp. 66–71 (2007)
Rodrigo, A., Peñas, A., Verdejo, F.: UNED at Answer Validation Exercise 2007. In: Working Notes of the CLEF 2007 Workshop, Budapest, Hungary (September 2007)
Kozareva, Z., Ferrández, O., Montoyo, A., Muñoz, R.: Combining data-driven systems for improving Named Entity Recognition. Data and Knowledge Engineering 61(3), 449–466 (2007)
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 2008 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Ferrández, Ó., Muñoz, R., Palomar, M. (2008). Improving Question Answering Tasks by Textual Entailment Recognition. In: Kapetanios, E., Sugumaran, V., Spiliopoulou, M. (eds) Natural Language and Information Systems. NLDB 2008. Lecture Notes in Computer Science, vol 5039. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-69858-6_37
Download citation
DOI: https://doi.org/10.1007/978-3-540-69858-6_37
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-69857-9
Online ISBN: 978-3-540-69858-6
eBook Packages: Computer ScienceComputer Science (R0)