Tailoring output to the user: What does user modelling in generation mean?

  • Karen Sparck Jones
Part of the The Kluwer International Series in Engineering and Computer Science book series (SECS, volume 119)

Abstract

This paper examines the implications, for linguistic output generation tailored to the interactive system user, of earlier analyses of the components of user modelling and of the constraints realism imposes on modelling. Using a range of detailed examples it argues that tailoring based only on the actual dialogue and on the decision model required for the system task is quite adequate, and that more ambitious modelling is both dangerous and unnecessary.

Keywords

User Modelling Decision Property System Task Computational Linguistics Patient Model 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

Bibliography

  1. Belkin, N.J., Seeger, T. and Wersig, G. `Distributed expert problem treatment as a model for information system analysis and design’, Journal of Information Science 5, 1983, 153–167.CrossRefGoogle Scholar
  2. Brooks, H.M. An intelligent interface for document retrieval systems: developing the problem description and retrieval strategy components, PhD Thesis, City University, London, 1986.Google Scholar
  3. Carbonell, J. et al. `The XCALIBUR project: a natural language interface to expert systems’, Proceedings of the Eighth International Joint Conference on Artificial Intelligence, 1983, 653–656.Google Scholar
  4. Chin, D.M. `KNOME: modelling what the user knows in UC’, in Kobsa and Wahlster (1989).Google Scholar
  5. Cohen, R. and Jones, M. `Incorporating user models into expert systems for educational diagnosis’, in Kobsa and Wahlster (1989).Google Scholar
  6. Daniels, P.J. Developing the user modelling function of an intelligent interface to document retrieval systems, PhD Thesis, City University, London, 1987.Google Scholar
  7. Grosz, B.J. and Sidner, C.L. `Assertions, intentions, and the structure of discourse’, Computational Linguistics 12, 1986, 175–204.Google Scholar
  8. Joshi, A., Webber, B. and Weischedel, R. `Preventing false inferences’, Proceedings of COLING84, 1984, 134–138.Google Scholar
  9. Kobsa, A. and Wahlster, W. (eds) User models in dialogue systems, Berlin: Springer, 1989.Google Scholar
  10. Litman, D.J. Plan recognition and discourse analysis: an integrated approach to understanding dialogues, PhD Thesis, TR 170, Department of Computer Science, University of Rochester, 1985.Google Scholar
  11. Morik, K. `User models and conversational settings: modelling the user’s wants’, in Kobsa and Wahlster (1989).Google Scholar
  12. Paris, C.L. `Tailoring object descriptions to a user’s level of expertise’, in Kobsa and Wahlster (1989).Google Scholar
  13. Pollack, M.E. Inferring domain plans in question answering, Technical Note 403, SRI International, Menlo Park, 1986.Google Scholar
  14. Rich, E. `Stereotypes and user modelling’, in Kobsa and Wahlster (1989).Google Scholar
  15. Sparck Jones, K. User models and expert systems, Technical Report 61, Computer Laboratory, University of Cambridge, 1984.Google Scholar
  16. Sparck Jones, K. `User models, discourse models, and some others’, Computational Linguistics 14, 1988, 98–100.Google Scholar
  17. Sparck Jones, K. `Realism about user modelling’, in Kobsa and Wahlster (1989); also Technical Report 111, Computer Laboratory, University of Cambridge, 1987Google Scholar
  18. Webber, B.L. `Questions, answers and responses: interacting with knowledge base systems’, in On knowledge base systems (ed Brodie and Mylopoulos), Berlin: Springer, 1986.Google Scholar
  19. Wilensky, R. et al. `The Berkeley UNIX Consultant project’, Computational Linguistics 14, 1988, 35–84.Google Scholar

Copyright information

© Springer Science+Business Media New York 1991

Authors and Affiliations

  • Karen Sparck Jones

There are no affiliations available

Personalised recommendations