2012 | OriginalPaper | Buchkapitel
DYNAMO-MAS: A Multi-Agent System for Building and Evolving Ontologies from Texts
verfasst von : Zied Sellami, Valérie Camps
Erschienen in: Advances on Practical Applications of Agents and Multi-Agent Systems
Verlag: Springer Berlin Heidelberg
Aktivieren Sie unsere intelligente Suche, um passende Fachinhalte oder Patente zu finden.
Wählen Sie Textabschnitte aus um mit Künstlicher Intelligenz passenden Patente zu finden. powered by
Markieren Sie Textabschnitte, um KI-gestützt weitere passende Inhalte zu finden. powered by
Building and evolving an ontology are a complex problems: they involve numerous entities (terms, concepts, relations), the environment of the ontology is dynamic (addition of new documents, ontologist’s actions) and we cannot predict all ontology evolution possibilities. That is why a unique entity or system to solve these problems cannot list all the possible situations to which it can be confronted as well as the actions it has to take in such situations. This compels to distribute the problem on several autonomous entities that have a local perception of each situation that can arise during the system functioning and that have simple, generic and local behaviors in order to self-adapt to these situations. We propose in that sense DYNAMO-MAS, a tool based on a Multi-Agent System (MAS) enabling the co-construction and the evolving of an ontology. It takes as input a corpus of texts and provides as output an ontology.