Abstract
Ontological concept Relation extraction is a difficult research problem. In this paper, we aim to extract multi-type relations from the text analyses and the existent relations (in the concept hierarchy). Our approach combines a verb centered method, lexical analyses, syntactic and statistic ones. It is based on a rich contextual modeling that strengthens the term co-occurrence selection, a lexical analysis, a use of the existent relations in the concept hierarchy and a stepping between the extracted relations to validate them and facilitate the evaluation made by the domain experts.
Chapter PDF
References
Nazarenko, A.: Compréhension du langage naturel: le problème de la causalité. Thèse de doctorat (1994)
Hearst, M.A.: Automatic acquisition of hyponyms from large text corpora. In: Proceedings of the fourteenth international conference on computational linguistics, Nantes, France, pp. 539–545 (1992)
Grefenstette, G.: Use of syntatic context to produce terms association list for text retrieval. In: SIGIR 1992. Conference in Research and Developement in Information Retrieval, Copenhagen, Denmarke, pp. 89–97 (juin 1992)
Bruandet, M.F.: Domain Knowledge Acquisition for an Intelligent Information Retrieval System: Strategies and Tools. Expert systems applications, 231–235 (1990)
Karoui, L., Aufaure, M.-A., Bennacer, N.: Context-based Hierachical Clustering for the Ontology Learning. In: IEEE Proceedings of the 2006 IEEE/WIC/ACM International Conference on Web Intelligence 2006, Hong-Kong, pp. 420–427 (2006)
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 2007 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Karoui, L., El Kadhi, N. (2007). Relation Extraction and Validation Algorithm. In: Janowski, T., Mohanty, H. (eds) Distributed Computing and Internet Technology. ICDCIT 2007. Lecture Notes in Computer Science, vol 4882. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-77115-9_33
Download citation
DOI: https://doi.org/10.1007/978-3-540-77115-9_33
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-77112-8
Online ISBN: 978-3-540-77115-9
eBook Packages: Computer ScienceComputer Science (R0)