Intuition as instinctive dialogue

  • Authors:
  • Daniel Sonntag

  • Affiliations:
  • German Research Center for Artificial Intelligence, Saarbrücken, Germany

  • Venue:
  • Computing with instinct
  • Year:
  • 2011

Quantified Score

Hi-index 0.00

Visualization

Abstract

A multimodal dialogue system which answers user questions in natural speech presents one of the main achievements of contemporary interaction-based AI technology. To allow for an intuitive, multimodal, task-based dialogue, the following must be employed: more than explicit models of the discourse of the interaction, the available information material, the domain of interest, the task, and/or models of a user or user group. The fact that humans adapt their dialogue behaviour over time according to their dialogue partners' knowledge, attitude, and competence poses the question for us what the influence of intuition in this natural human communication behaviour might be. A concrete environment, where an intuition model extends a sensory-based modelling of instincts can be used and should help us to assess the significance of intuition in multimodal dialogue. We will explain the relevant concepts and references for self-study and offer a specific starting point of thinking about intuition as a recommendation to implement complex interaction systems with intuitive capabilities. We hope this chapter proposes avenues for future research to formalise the concept of intuition in technical, albeit human-centred, AI systems.