TSD 2010: Text, Speech and Dialogue pp 125-132 | Cite as
Question Answering for Not Yet Semantic Web
Conference paper
Abstract
In this paper we present a prototype implementation of the question answering system for one of the inflectional languages – Czech. The presented open domain system is especially effective in answering factual wh-questions about people, dates, names and locations. The answer is constructed on-the-fly from data gathered from the Internet, public ontologies, knowledge of the Czech language, and extensible template system. The system is capable of semiautomatic learning of new templates as well as both statistical and semantic processing of Internet content.
Keywords
question answering information extraction machine learning NLP morphology semantic compatibilityPreview
Unable to display preview. Download preview PDF.
References
- 1.Berners-Lee, T., Hendler, J., Lassila, O.: The Semantic Web. Sci. Am. Mag. (2001)Google Scholar
- 2.Shadbolt, N., Hall, W., Berners-Lee, T.: The Semantic Web Revisited. IEEE Intelligent Systems (2006)Google Scholar
- 3.Ravichandran, D., Hovy, E.: Learning Surface Text Patterns for a Question Answering System. In: Proceedings of the 40th ACL, pp. 41–47. ACL, Philadelphia (2002)Google Scholar
- 4.Svoboda, L., Popelínský, L.: Communication with WWW in Czech. Kybernetika 40 (2004)Google Scholar
- 5.Pala, K., Smrž, P.: Building Czech Wordnet. Romanian Journal of Information Science and Technology 2004 (7), 79–88 (2004)Google Scholar
- 6.Habernal, I., Konopík, M.: Active Tags for Semantic Analysis. In: Sojka, P., Horák, A., Kopeček, I., Pala, K. (eds.) TSD 2008. LNCS (LNAI), vol. 5246, pp. 69–76. Springer, Heidelberg (2008) ISBN 978-3-540-87390-7CrossRefGoogle Scholar
Copyright information
© Springer-Verlag Berlin Heidelberg 2010