Detection of assessment patterns in ordinary triadic conversation

  • Authors:
  • Katsuya Takanashi;Eiki Fujimoto;Yasuyuki Kono;Kazuhiro Takeuchi;Hitoshi Isahara

  • Affiliations:
  • Kyoto University, Kyoto, Japan;Nara Institute of Science and Technology, Ikoma City, Nara, Japan;Nara Institute of Science and Technology, Ikoma City, Nara, Japan;National Institute of Information and Communications Technology, Kyoto, Japan;National Institute of Information and Communications Technology, Kyoto, Japan

  • Venue:
  • JSAI'05 Proceedings of the 2005 international conference on New Frontiers in Artificial Intelligence
  • Year:
  • 2006

Quantified Score

Hi-index 0.00

Visualization

Abstract

Recent interests in conversation in the field of artificial intelligence have expanded beyond the development of particular task-oriented dialogue systems toward technologies for supporting human-human communication in various circumstances. Within such communication supportive approaches, the importance of the analysis of multiparty conversation has increasingly been recognized. In accordance with these orientations, this article outlines a three-party conversation corpus built by the National Institute of Information and Communications Technology, and introduces three preliminary analyses of it that will contribute to the development of Conversational Informatics: The characteriscits of turn-taking procedure in three-person conversation; assessment sequential patterns that appeared in the data; and shared knowledge and interpersonal relationships between participants observable from the assessment sequences in triadic conversation.