Agent-supported information retrieval for natural language

This paper addresses issues in using modeling techniques for a multi-agent system, which adapts and extends existing object-orientated (OO) representation techniques for parsing natural language. After concentrating on the main problems of natural language information retrieval, we focus on the details of the applied agent-orientated modeling techniques and assume a passing familiarity with OO modeling and representation techniques. In addition to the above, we discuss the utility of having a matchmaking agent which can reason over agent capabilities to recommend agents for specific tasks, where the capabilities and requirements are defined using a common service ontology. This ensures that the semantics of matching agent capabilities remains the same across the multi-agent system.