An Ontology-based Architecture for Cooperative Information Agents

In the Web, extractor agents process classes of pages (like 'call for papers' pages, researchers' pages, etc), neglecting the relevant fact that some of them are interrelated forming clusters (e.g., science). We propose here an architecture for cognitive multi-agent systems to retrieve and classify pages from these clusters, based on data extraction. To enable cooperation, two design requirements are crucial: (a) a Web vision coupling a vision for contents (classes and attributes to be extracted) to a functional vision (the role of pages in information presentation); (b) explicit representation of agents' knowledge and abilities in the form of ontologies, both about the cluster's domain and agents' tasks. Employing this Web vision and agents' cooperation can accelerate the retrieval of useful pages. We got encouraging results with two agents for the page classes of scientific events and articles. A comparison of results to similar systems comes up with two requirements for such systems: functional categorization and a thoroughly detailed ontology of the cluster.