DYNAMO-MAS: a multi-agent system for ontology evolution from text

Zied Sellami (1) , Valérie Camps (2, 3) , Nathalie Aussenac-Gilles (1, 4)

1 IRIT-MELODI - MEthodes et ingénierie des Langues, des Ontologies et du DIscours
2 IRIT-SMAC - Systèmes Multi-Agents Coopératifs
3 UT3 - Université Toulouse III - Paul Sabatier
4 CNRS - Centre National de la Recherche Scientifique

Manual ontology development and evolution are complex and time-consuming tasks, even when textual documents are used as knowledge sources in addition to human expertise or existing ontologies. Processing natural language in text produces huge amounts of linguistic data that need to be filtered out and structured. To support both of these tasks, we have developed DYNAMO-MAS, an interactive tool based on an adaptive multi-agent system (adaptive MAS or AMAS) that builds and evolves ontologies from text. DYNA-MO-MAS is a partner system to build ontologies; the ontologist interacts with the system to validate or modify its outputs. This paper presents the architecture of DYNAMO-MAS, its operating principles and its evaluation on three case studies.

Mots clés: Ontology evolution; Ontology engineering from text; Adaptive multi-agent system

Domaines: Intelligence artificielle [cs.AI]; Système multi-agents [cs.MA]

Zied Sellami, Valérie Camps, Nathalie Aussenac-Gilles. DYNAMO-MAS: a multi-agent system for ontology evolution from text. Journal on Data Semantics, 2013, 2 (2-3), pp.145-161. ⟨10.1007/s13740-013-0025-1⟩. ⟨hal-01137318⟩