Enrichissement de bases de connaissances par l'annotation sémantique

In this paper we present a new form of Semantic Web portal using Human Language Technologies (HLT). Our system provides the means to annotate documents with metadata, populate a knowledge base according to the corresponding domain ontology and most of all, update the linguistic resources with all the new extracted information in order to improve the performance of the entire system. As a consequence, it will assist the Web communities, and among them the competitive intelligence workers, to create domain-centric Semantic Web portals. The final user will be able, through the application's interfaces, to visualise the knowledge base's instances, to formulate complex queries and at least, to publish the returned results. We would like to point out the fact that the entire platform is Semantic Web-compliant as it is based on its standards (XML, XTM, RDF(S) and OWL).