Abstract
An automatic method for generation of semantic patterns from free-text questions is proposed in this paper. An evaluation method is also proposed to estimate the suitability of the generated patterns and implemented in our user-interactive question answering (QA) system. Experiments with 5500 questions show that 63.9% generated patterns are satisfactory in the average.
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
Google Answers (2007), http://answers.google.com/answers/
Microsoft QnA (2007), http://qna.live.com/
Yahoo Answers (2007), http://answers.yahoo.com/
Deepak, R., Eduard, H.: Learning Surface Text Patterns for a Question Answering System. In: Proceedings of the 40th ACL Conference, Philadelphia (2002)
Cowie, J., Ludovik, E., Molina-Salgado, H., Nirenburg, S., Sheremetyeva, S.: Automatic Question Answering. In: Proceedings of the Rubin Institute for Advanced Orthopedics Conference, Paris (2000)
Hao, T.Y., Hu, D.W., Liu, W.Y., Zeng, Q.T.: Semantic Patterns for User-Interactive Question Answering. Journal of Concurrency and Computation: Practice and Experience 20(1) (2007)
BuyAns (2007), http://www.buyans.com
5500 Question list (2007), http://l2r.cs.uiuc.edu/~cogcomp/Data/QA/QC/train_5500.label
WordNet (2007), http://wordnet.princeton.edu/
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 2008 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Hao, T., Song, W., Hu, D., Liu, W. (2008). Automatic Generation of Semantic Patterns for User-Interactive Question Answering. In: Li, H., Liu, T., Ma, WY., Sakai, T., Wong, KF., Zhou, G. (eds) Information Retrieval Technology. AIRS 2008. Lecture Notes in Computer Science, vol 4993. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-68636-1_75
Download citation
DOI: https://doi.org/10.1007/978-3-540-68636-1_75
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-68633-0
Online ISBN: 978-3-540-68636-1
eBook Packages: Computer ScienceComputer Science (R0)