Mixed-Initiative Ontology Learning

This paper presents a mixed-initiative assistant that supports a subject matter expert to extend the ontology of a learning agent, in order to express the subtle distinctions he makes in an application domain. This assistant performs a comparative analysis of the correct examples and the exceptions accumulated by the problem solving rules and guides the expert in improving its knowledge base. This assistant is integrated into the Disciple-RKF system, and has been evaluated in two knowledge acquisition experiments performed at the US Army War College.

• Type: Conference
• Year: 2004
• Where: ICAI
• Authors: Cristina Boicu, Gheorghe Tecuci
• Keywords: ICAI 2004, ICAI 2007, Mixed-initiative Assistant, Subject Matter Expert, US Army War College