An Evidential Model for Tracking Initiative in Collaborative Dialogue Interactions

  • Authors:
  • Jennifer Chu-Carroll;Michael K. Brown

  • Affiliations:
  • Bell Laboratories, Lucent Technologies, 600 Mountain Avenue, Murray Hill, NJ 07974, U.S.A./ e-mail: Email: &lcub/jencc,mkb&rcub/@bell-labs.com;Bell Laboratories, Lucent Technologies, 600 Mountain Avenue, Murray Hill, NJ 07974, U.S.A./ e-mail: Email: &lcub/jencc,mkb&rcub/@bell-labs.com

  • Venue:
  • User Modeling and User-Adapted Interaction
  • Year:
  • 1998

Quantified Score

Hi-index 0.00

Visualization

Abstract

In this paper, we argue for the need to distinguish between task initiative and dialogue initiative, and present an evidential model for tracking shifts in both types of initiatives in collaborative dialogue interactions. Our model predicts the task and dialogue initiative holdersfor the next dialogue turn based on the current initiative holders and the effect that observed cues have on changing them. Our evaluation across various corpora shows that the use of cues consistently provides significant improvement in the system‘s prediction of task and dialogue initiative holders. Finally, we show how this initiative tracking model may be employed by a dialogue system to enable the system to tailor its responses to user utterances based on application domain, system‘s role in the domain, dialogue history, and user characteristics.