Toyoaki Nishida,
Hideaki Takeda, Kenji Iino, Michiaki Iwadume, Katsuji Onishi, Tadahisa Okimoto,
Yoichi Kado, Motoyuki Takaai, Kazuhiro Takaoka, Masatoshi Nishiki,
Kenji Hanakawa, Shoji Yasumura
Graduate School of Information Science, Nara Institute of Science and Technology
8916-5 Takayama, Ikoma, Nara 630-01, Japan
e-mail: nishida@is.aist-nara.ac.jp
In this research, we focus on commonsense knowledge referred to in spoken dialogue. We attempt to build a computational model of commonsense knowledge and develop a knowledge server that can provide commonsense knowledge for various components of spoken dialogue system. In this fiscal year, we have made a study on large scale knowledge sharing, and proposed a framework called the Knowledgeable Community based on multi-agent architecture. The Knowledgeable Community, is characterized by ontology oriented agent organization and multi-stage mediation mechanism. Ontology oriented agent organization means that agents are associated with ontologies, structural definitions of concepts. A mediation mechanism is provided for mediating agents looking for a service with those providing the service by combining concept similarity and definition. In order to derive even in the course of development, we propose building up the Knowledgeable Community in a bottom up manner. Currently, implementation of the first version of the Knowledgeable Community is in progress using platforms developed.
Keywords: commonsense knowledge, knowledge sharing and reuse, multi-argent, mediation