Armadillo : harvesting information for the semantic web

Abstract

Armadillo is an automatic system for producing domain- specific Semantic Web oriented annotation on large repositories. It annotates by extracting information from different sources and integrating it into a knowledge base. Such base can then be used both to access the information directly (e.g. via a semantic web agent) and to annotate the pages where the information was identified. Armadillo is adaptive: it learns how to harvest information with minimal initial user intervention.