Conversation quantisation for conversational knowledge process

  • Authors:

  • Toyoaki Nishida

  • Affiliations:

  • Department of Intelligence Science and Technology, Graduate School of Informatics, Kyoto University, Yoshida-Honmachi, Sakyo-ku, Kyoto 606-8501, Japan

  • Venue:
  • International Journal of Computational Science and Engineering
  • Year:
  • 2007

Quantified Score

Hi-index 0.00

Visualization

Abstract

I present an approach on conversational knowledge process based on conversation quantisation, which is a technique of approximating a continuous flow of conversation by a series of conversation quanta that represent points of the discourse. Conversation quantisation allows for implementing a rather robust conversation system by basing it on the large amount of conversational quanta collected from the real world. I describe techniques for extracting conversation quanta from the real-world conversation, spatially accumulating them for visual manipulation, and using conversation quanta to drive embodied conversational agents.