Combining agents and Wrapper Induction for information gathering on restricted web domains

Web is growing constantly and exponentially every day. Thus, gathering relevant information becomes unfeasible. Existent indexing-based search engines ignore information context, which is essential to deciding on its relevance. Restraining to a single web domain, domain ontology can be used to take into consideration the related context, the fact that might enable treating web pages that belong to the considered domain more intelligently. Nevertheless, symbolic rules that exploit domain´s ontology to realize this treatment are delicate and fastidious to develop, especially for information extraction task. This paper presents Boosted Wrapper Induction (BWI), a machine learning method for adaptive information extraction, and its exploitation as a replacement of the symbolic approach for information extraction task in AGATHE, a generic multi-agent architecture for information gathering on restrained web domains.