Abstract
In this study, we describe how to extract a sentence which serves as a correct answer for a how-to question about actions to be taken on the Web. The distinguishing feature of this study is the extraction of sentences using a set of queries, after collecting queries considered to be effective for answer extraction. By using a query set, it is possible to extract the answer considered to express the contents of the Web page pertinent to the question. In the results of the experiment, the average recall was 77.3% and the average precision was 62.9%.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Kupiec, J.: MURAX: Finding and Organizing Answers from Text Search. In: Strzalkowsky, T. (ed.) Natural Language Information Retrieval, pp. 311–332. Kluwer Academic Publishers (1999)
Asanoma, N., Furuse, O., Kataoka, R.: Feature Analysis of Explanatory Documents for How-to Type Question Answering. Information Processing Society of Japan, 55–60 (2005)
Murdock, V., Kelly, D., Croft, W.B., Belkin, N.J., Yuan, X.: Identifying and improving retrieval for procedural questions. Information Processing and Management 43(1), 181–203 (2007)
Masanori, Y., Kanamori, K., Fukuda, M., Nobesawa, S., Tahara, I.: Extraction of Descriptive Parts Based on Chains of Action Expressions. Institute of Electronics, Information, and Communication Engineers, p. 53 (2007)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2012 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Ishikawa, K., Ohwada, H. (2012). Extraction of How-to Type Question-Answering Sentences Using Query Sets. In: Richards, D., Kang, B.H. (eds) Knowledge Management and Acquisition for Intelligent Systems. PKAW 2012. Lecture Notes in Computer Science(), vol 7457. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-32541-0_11
Download citation
DOI: https://doi.org/10.1007/978-3-642-32541-0_11
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-32540-3
Online ISBN: 978-3-642-32541-0
eBook Packages: Computer ScienceComputer Science (R0)