Predictive Role Taking in Dialog: Global Anticipation Feedback Based on Transmutability

By Alassane Ndiaye and Anthony Jameson (1996)

In S. Carberry & I. Zukerman (Hrsg.), Proceedings of the Fifth International Conference on User Modeling (S. 137–144). Boston, MA: User Modeling, Inc.

Abstract

Human dialog participants regularly predict the responses of their dialog partners by hypothetically assuming the partner’s role. This strategy of using global anticipation feedback has seldom been approximated in dialog systems. In the system PRACMA, the technical prerequisites for this strategy have been fulfilled, and the system is being used as a testbed to explore the potential and limitations of the strategy. This paper first introduces a theoretical framework for analyzing possible realizations of global anticipation feedback. It then shows how the strategy can be realized in a dialog system that is capable of taking both roles within its dialog situation. An extension of these techniques is discussed that addresses the limited predictability of users’ responses. The final section discusses several approaches to minimizing the computational cost of using global anticipation feedback.

Citations

• Google Scholar page

Download

Full Publication:  

BibTeX entry

@incollection{NdiayeJ96,
  year = {1996},
  author = {{Ndiaye}, Alassane and
            {Jameson}, Anthony},
  editor = {{Carberry}, Sandra and
            {Zukerman}, Ingrid},
  title = {Predictive Role Taking in Dialog: Global Anticipation Feedback Based on Transmutability},
  booktitle = {{Proceedings of the Fifth International Conference on User Modeling}},
  address = {Boston, MA},
  publisher = {User Modeling, Inc.},
  pages = {137--144}}