Multi-agent systems for ontology-based information retrieval

The Web offers a huge amount of valuable information, but it is very hard and time consuming to retrieve thousands of web pages related to a concept, filter the relevant ones, analyse this information and integrate it in a knowledge repository. This paper describes one component of a knowledge management platform (h-TechSight project) that performs these tasks, the multi-agent search module (MASH). MASH employs a domain ontology to search for web pages that contain relevant information to each concept in the domain of interest. The search is then constrained to a specific domain to avoid as much as possible the analysis of irrelevant information.