A User Modeling Approach to Determining System Initiative in Mixed-Initiative AI Systems

  • Michael Fleming
  • Robin Cohen
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 2109)


In this paper, we address the problem of providing guidelines to designers of mixed-initiative artificial intelligence systems, which specify when the system should take the initiative to solicit further input from the user, in order to carry out a problem solving task. We first present a utility-based quantitative framework which is dependent on modeling: whether the user has the knowledge the system is seeking, whether the user is willing to provide that knowledge and whether the user would be capable of understanding the request for information from the system. Examples from the application of sports scheduling are included. We also discuss a qualitative version of the model, for applications with sparse data. This paper demonstrates a novel use for user models, one in which the system does not simply alter its generation based on the user model, but in fact makes a user-specific decision about whether to interact at all.


mixed-initiative systems dialogue exploiting user models to adapt interaction interactive scheduling clarification tailoring generation 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    D. Anderson, E. Anderson, N. Lesh, J. Marks, B. Mirtich, D. Ratajczak, and K. Ryall. Humanguided simple search. In Proceedings of AAAI-2000, pages 209–216. AAAI Press, 2000.Google Scholar
  2. 2.
    L. Ardissono and D. Sestero. Using dynamic user models in the recognition of the plans of the user. User Modeling and User Adapated Interaction, 5(2):157–190, 1996.CrossRefGoogle Scholar
  3. 3.
    S. Carberry, J. Chu-Carroll, and S. Elzer. Constructing and utilizing a model of user preferences in collaborative consultation dialogues. Computational Intelligence, 15(3):185–217, 1999.CrossRefGoogle Scholar
  4. 4.
    E. Horvitz. Principles of mixed-initiative user interfaces. In Proceedings of CHI’ 99, ACM SIGCHI Conference on Human Factors in Computing Systems, Pittsburgh, PA, pages 159–166. ACM Press, 1999.Google Scholar
  5. 5.
    N. Lesh, C. Rich, and C.L. Sidner. Using plan recognition in human-computer collaboration. In Proceedings of UM’99, Banff, Alberta, Canada, pages 23–32, 1999.Google Scholar
  6. 6.
    D. Litman and S. Pan. Empirically evaluating an adaptable spoken dialogue system. In Judy Kay, editor, Proceedings of UM’99, Banff, Alberta, Canada, pages 55–64, 1999.Google Scholar
  7. 7.
    C. Paris. The role of the user’s domain knowledge in generation. Computational Intelligence, 7(2):71–93, 1991.CrossRefMathSciNetGoogle Scholar
  8. 8.
    B. Raskutti and I. Zukerman. Query and response generation during information-seeking interactions. In Proceedings of UM’94, Hyannis, Mass, pages 25–30, 1994.Google Scholar
  9. 9.
    D. Sullivan, B. Grosz, and S. Kraus. Intention reconciliation by collaborative agents. In Proceedings of ICMAS-2000, pages 293–300. IEEE Computer Society Press, 2000.Google Scholar
  10. 10.
    M. Walker, D. Litman, C. Kamm, and A. Abella. PARADISE: A framework for evaluating spoken dialogue agents. In Proceedings of the 35th Annual Meeting of the Association of Computational Linguistics, pages 271–280, 1997.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2001

Authors and Affiliations

  • Michael Fleming
    • 1
  • Robin Cohen
    • 1
  1. 1.Department of Computer ScienceUniversity of WaterlooWaterlooCanada

Personalised recommendations