Flexible Generation: Taking the User into Account

  • Cécile L. Paris
  • Vibhu O. Mittal
Part of the Linguistica Computazionale book series (LICO, volume 9)


Sophisticated computer systems capable of interacting with people using natural language are becoming increasingly common. These systems need to interact with a wide variety of users in different situations. Typically, these systems have access to large amounts of data and must select from these data the information to present to the user. No single generated text will be adequate across all user types and all situations. Certainly, people plan what they will say or write based in part on their knowledge of the listener or intended reader. Similarly, computer systems that produce language must take their listeners/readers into account in order to be effective. In particular, the user’s level of knowledge about the domain of discourse is an important factor in this tailoring, if the text provided is to be both informative and understandable to the user. The text should not contain information that is already known or can be easily inferred, nor should it include facts that the user cannot understand. This paper demonstrates the feasibility of incorporating the user’s domain knowledge or user’s expertise, into a text generation system and addresses the issue of how this factor might affect the content, organization and phrasing of a text. We look at two applications domains: (i) generating descriptions of complex physical objects, and (ii) generating documentation for programming languages. We show how a computer generation system can make use of both stereotypical and individualized user models.


User Model Advanced User Intended Reader Empty List Plan Recognition 
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.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. [1]
    Paul W. Abrahams, Karl Berry, and Kathryn A. Hargreaves. TEX for the Impatient. Addison-Wesley Publishing Co., 1990.Google Scholar
  2. [2]
    John A. Bateman and Cécile L. Paris. Phrasing a Text in Terms the User Can Understand. In Proceedings of IJCAI’89, Detroit, MI, 1989, pp. 1511–1517.Google Scholar
  3. [3]
    John A. Bateman and Cécile L. Pans. Constraining the Deployment of Lexicogrammatical Resources During Text Generation: Towards a Computational Instantiation of Register Theory. In Eija Ventola, Editor, Functional and Systemic linguistics: Approaches and Uses, pp. 81–106. Mouton de Gruyter, Berlin, 1991.Google Scholar
  4. [4]
    Sandra Carberry. Plan recognition in Natural Language Dialogue. MIT Press Cambridge, MA, 1990.Google Scholar
  5. [5]
    Chevrolet. Chevrolet Service Manual, General Motors Corporation, 1978, Detroit, MI.Google Scholar
  6. [6]
    David N. Chin. KNOME: Modeling What the User Knows in UC. In Alfred Kobsa and Wolfgang Wahlster, editors, User Models in Dialog Systems. Springer Verlag, Berlin, 1989.Google Scholar
  7. [7]
    Collier’s Encyclopedia, New York, Crowell-Collier Publishing Company 1962.Google Scholar
  8. [8]
    Reader’s Digest, September 1989. Contributed by Arlene Shovald.Google Scholar
  9. [9]
    Katherine Voerwerk Feldman and Herbert J. Klausmeier. The Effects of Two Kinds of Definitions on the Concept Attainment of Fourth-and Eighth-grade Students. Journal of Educational Research,67(5):219–223, 1974.Google Scholar
  10. [10]
    Bradley A. Goodman and Diane J. Litman. On the Interaction Between Plan Recognition and Intelligent Interfaces. User Modeling and User-Adapted Interaction, 2 (1–2): 55–82, 1992.Google Scholar
  11. [11]
    J. E. Grimes. The Thread of Discourse. Mouton, The Hague, 1975.Google Scholar
  12. [12]
    Robert Kass. Building a User Model Implicitly from a Cooperative Advisory Dialog. User Modeling and User-Adapted Interaction, 1 (3): 203–258, 1991.CrossRefGoogle Scholar
  13. [13]
    The New Book of Knowledge - The Children’s Encyclopedia, 1967. Grolier Inc., New York.Google Scholar
  14. [14]
    Alfred Kobsa. Generating a User Model from WH-Questions in the VIE-LANG System. Technical Report 84–03, Department of Medical Cybernetics, University of Vienna, 1984.Google Scholar
  15. [15]
    Wendy G. Lehnert. The Process of Question Answering. Lawrence Erlbaum Associates, Hillsdale, NJ, 1978.Google Scholar
  16. [16]
    William C. Mann and Sandra A. Thompson. Rhetorical Structure Theory: Towards a Functional Theory of Text Organization. TEXT, 8 (3): 243–281, 1988.Google Scholar
  17. [17]
    Kathleen R. McKeown. Text Generation: Using Discourse Strategies and Focus Constraints to Generate Natural Language Text. Cambridge University Press, Cambridge, England, 1985.Google Scholar
  18. [18]
    Kathleen R. McKeown. Generating Goal-Oriented Explanations. International Journal of Expert Systems, 1 (4): 377–395, 1988.Google Scholar
  19. [19]
    Vibhu O. Mittal. “Generating Descriptions with Integrated Text and Examples.” PhD thesis, University of Southern California, Los Angeles, CA, 1993.Google Scholar
  20. [20]
    Vibhu O. Mittal and Cécile L. Paris. Generating Natural Language Descriptions with Examples: Differences between Introductory and Advanced Texts. Proceedings of the Eleventh National Conference on Artificial Intelligence — AAA’ 93, 1993.Google Scholar
  21. [21]
    Vibhu O. Mittal and Cécile L. Paris. The Placement of Examples in Descriptions: Before, Within or After the Text. Proceedings of First Pacific Association for Computational Linguistics Conference,Vancouver, Canada, May 1993, pp. 279287.Google Scholar
  22. [22]
    Johanna D. Moore and Cécile L. Paris. Planning Text for Advisory Dialogues: Capturing Intentional, and Rhetorical Information. Computational Linguistics, 19(4): 651–694, December 1993.Google Scholar
  23. [23]
    Cécile L. Paris. Tailoring Object Descriptions to the User’s Level of Expertise. Computational Linguistics, 14 (3): 64–78, September 1988.Google Scholar
  24. [24]
    Cécile L. Paris. User Modeling in Text Generation. Frances Pinter, 1993.Google Scholar
  25. [25]
    Elaine Rich. User Modeling via Stereotypes. Cognitive Science, 3: 329–354, 1979.CrossRefGoogle Scholar
  26. [26]
    UNIX Documentation. UNIX User’s Reference Manual 4.3 Berkeley Software Distribution. Computer Systems Research Group, Computer Science Division, University of California, Berkeley, CA, 1986.Google Scholar
  27. [27]
    H. R. Shepherd. The Fine Art of Writing. Macmillan, New York, 1926.Google Scholar
  28. [28]
    Stedman’s Medical Dictionary, 24th Edition. Williams and Wilkins, Baltimore, London, Los Angeles, Sydney, 1982.Google Scholar
  29. [29]
    Guy L. Steele Jr. Common Lisp: The Language. Digital Press, 1984.Google Scholar
  30. [30]
    David S. Touretzky. LISP: A Gentle Introduction to Symbolic Computation. Harper & Row, New York, 1984.Google Scholar
  31. [31]
    Peter van Beek. A Model for Generating Better Explanations. Proceedings of ACL 1987, Palo Alto, California, 1987.Google Scholar
  32. [32]
    Webster’s New Twentieth Century Dictionary, Second Edition. New World D:’ictionaries. New York, 1979.Google Scholar
  33. [33]
    A. Weissler and P. Weissler. A Woman’s Guide to Fixing the Car. Walker and Company, New York, 1973.Google Scholar
  34. [34]
    W. Woods. An Experimental Parsing System for Transition Network Grammars. In R. Rustin, editor, Natural Language Processing. Algorithmics Press, New York, 1973.Google Scholar

Copyright information

© Springer Science+Business Media Dordrecht 1994

Authors and Affiliations

  • Cécile L. Paris
    • 1
    • 2
  • Vibhu O. Mittal
    • 3
  1. 1.Information Sciences InstituteUSCUSA
  2. 2.Information Technology Research InstituteUniversity of BrightonUSA
  3. 3.Intelligent Systems Lab Department of Computer ScienceUniversity of PittsburghUSA

Personalised recommendations