Abstract

Because the World Wide Web consists primarily of text, information extraction is central to any effort that would use the Web as a resource for knowledge discovery. We show how information extraction can be cast as a standard machine learning problem, and argue for the suitability of relational learning in solving it. The implementation of a general-purpose relational learner for information extraction, SRV, is described. In contrast with earlier learning systems for information extraction, SRV makes no assumptions about document structure and the kinds of information available for use in learning extraction patterns. Instead, structural and other information is supplied as input in the form of an extensible token-oriented feature set. We demonstrate the effectiveness of this approach by adapting SRV for use in learning extraction rules for a domain consisting of university course and research project pages sampled from the Web. Making SRV Web-ready only involves adding several simple...

Citations

784	Learning logical definitions from relations - Quinlan - 1989
682	The CN2 induction algorithm - Clark, Niblett - 1989
460	Wrapper induction for information extraction - Kushmerick, Weld, et al. - 1997
279	Doorenbos, “A Scalable Comparison Shopping Agent for The World Wide Web - Etzioni, Weld, et al. - 1996
277	Bottom-up relational learning of pattern matching rules for information extraction - Califf, Mooney - 2003
147	Estimating Probabilities: A Crucial Task in Machine Learning - Cestnik - 1990
92	Empirical methods in information extraction - Cardie - 1997
42	Toward General-Purpose Learning for Information Extraction - Freitag - 1998
32	Learning Text Analysis Rules for Domain-Specific Natural Language Processing - Soderland - 1997