POPEL — A Parallel and Incremental Natural Language Generation System

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


This contribution presents an overview of POPEL, a natural language generation system that is part of the XTRA dialog system. POPEL’s main features are: bidirectional interaction between the “what-to-say” and the “how-to-say” components, incremental selection and realization of the utterance, and the generation of pointing gestures adapted to the user. The “whatto-say” component consists of a selector which determines the conceptual content, an activator which passes the conceptual units to the realizer, a request handler for requests resulting from the verbalization process, and a context handler which handles the choice of descriptions. The decisions made by these components are based heavily on contextual knowledge. The “how-to-say” component is especially designed for the requirements of POPEL. Using intermediate linguistic based descriptions, it translates the non-linguistically oriented representation of the content into natural language. The gesture generator ZORA determines and visualizes pointing gestures based on domain dependent rules. POPEL is realized on a (simulated) parallel processor.


Noun Phrase Knowledge Source Active Object Computational Linguistics Contextual Knowledge 
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]
    J. Allgayer. £SB-ONE+Die Zugangssprache zu SB-ONE { . Memo, Univ. des Saarlandes, 1989.Google Scholar
  2. [2]
    J. Allgayer. Eine Graphikkomponente zur Integration von Zeigehandlungen in natürlichsprachliche KI-Systeme. In Proceedings der 16. GI-Jahrestagung, pages 284–298, Springer, Berlin, 1986.Google Scholar
  3. [3]
    J. Allgayer, R. Jansen-Winkeln, C. Reddig, and N. Reithinger. Bidirectional use of knowledge in the multi-modal NL access system XTRA. In 11. IJCAI, Morgan Kaufmann, Los Angeles, CA., 1989.Google Scholar
  4. [4]
    D. Appelt. Planning English Sentences. Cambridge University Press, Cambridge, 1985.CrossRefGoogle Scholar
  5. [5]
    K. DeSmedt and G. Kempen. The representation of grammatical knowledge in a model for incremental sentence generation. In Natural Language Generation in Artificial Intelligence and Computational Linguistics, (this volume). Paris, Swartout, Mann (Eds). Kluwer Academic Publishers, Norwell, MA, 1990.Google Scholar
  6. [6]
    U. Engel. Deutsche Grammatik. Julius Groos, Heidelberg, 1988.Google Scholar
  7. [7]
    W. Finkler and G. Neumann. MORPHIX — a fast realization of a classification-based approach to morphology. In Harald Trost, editor, 4. Österreichische Artificial-Intelligence-Tagung, Wiener Workshop Wissensbasierte Sprachverarbeitung, pages 11–19, Springer, Berlin, 1988.Google Scholar
  8. [8]
    W. Finkler and G. Neumann. POPEL-HOW — a distributed parallel model for incremental natural language production with feedback. In 11. IJCAI, Morgan Kaufmann, Los Angeles, CA., 1989.Google Scholar
  9. [9]
    B.J. Grosz and C.L. Sidner. Attention, intentions, and the structure of discourse. Computational Linguistics, 12 (3): 175–204, July—September 1986.Google Scholar
  10. [10]
    E. Hovy. Generating Natural Language Under Pragmatic Constraints. PhD thesis, Yale University, 1987.Google Scholar
  11. [11]
    J. Jung, A. Kresse, N. Reithinger, and R. Schäfer. Das System ZORA — Wissensbasierte Generierung von Zeigegesten. In D. Metzing, editor, GWAI-89, Springer, Berlin, 1989.Google Scholar
  12. [13]
    R. Kass and T. Finin. The need for user models in generating expert system explanations. Technical Report MS-CIS-87–86, Department of Computer and Information Science, University of Philadelphia, 1987.Google Scholar
  13. [13]
    A. Kobsa. Benutzermodellierung in Dialogsystemen. Springer, Berlin, 1985.Google Scholar
  14. [14]
    A. Kobsa. The SB-ONE representation workbench. In Workshop on formal aspects of semantic networks, Santa Catalina Island, CA., 1989.Google Scholar
  15. [15]
    A. Kobsa and W. Wahlster, editors. User Models in Dialog Systems. Symbolic Computation Series, Springer, Berlin, 1988.Google Scholar
  16. [16]
    W.C. Mann and S.A. Thompson. Rhetorical Structure Theory: A Theory of Text Organisation. Technical Report ISI/RS-87–190, USC/ISI, Marina del Rey, CA., 1987.Google Scholar
  17. [17]
    D.D. McDonald. Surface generation for a variety of applications. In National Computer Conference, pages 105–110, 1985.Google Scholar
  18. [18]
    K.R. McKeown. Text generation. Cambridge University Press, Cambridge, 1985.CrossRefGoogle Scholar
  19. [19]
    J.D. Moore and W.R. Swartout. A reactive approach to explanation: Taking the user’s feedback into account. In Natural Language Generation in Artificial Intelligence and Computational Linguistics(this volume). Paris, Swartout, Mann (Eds). Kluwer Academic Publishers, Norwell, MA, 1990. Google Scholar
  20. [20]
    C.L. Paris. Generation and explanation: building an explanation facility for the explainable expert systems framework. In Natural Language Generation in Artificial Intelligence and Computational Linguistics, (this volume). Paris, Swartout, Mann (Eds). Kluwer Academic Publishers, Norwell, MA, 1990.Google Scholar
  21. [21]
    L. Polanyi. The Linguistic Discourse Model: Towards a Formal Theory of Discourse Structure. Technical Report 6409, BBN Laboratories, Cambridge, MA., 1986. Google Scholar
  22. [22]
    -J. Profitlich. SB-ONE: Ein Wissensrepräsentationssysiem basierend auf KL-ONE. Master’s thesis, Universität des Saarlandes, Saarbrücken, 1989.Google Scholar
  23. [23]
    R. Reichman. Getting Computers to Talk Like You and Me. MIT Press, Cambridge, MA., 1985.Google Scholar
  24. [24]
    N. Reithinger. Dialogstrukturen in XTRA. Memo, Universität des Saarlandes, Saarbrücken, 1989. To appear.Google Scholar
  25. [25]
    N. Reithinger. Generating referring expressions and pointing gestures. In Gerard Kempen, editor, Natural Language Generation, pages 71–81, Martinus Nijhoff, Dordrecht, 1987.CrossRefGoogle Scholar
  26. [26]
    D. Schmauks and N. Reithinger. Generating multimodal output — conditions, advantages and problems. In 12th COLING, pages 584–588, Budapest, 1988.Google Scholar
  27. [27]
    P. Sgall, E. Hajicovâ, and J. Panevovâ. The Meaning of the Sentence in its Semantic and Pragmatic Aspects. Reidel, Dordrecht, 1987.Google Scholar
  28. [28]
    S.M. Shieber, H. Uszkoreit, F.C.N Pereira, J.J. Robinson, and M. Tyson. The formalism and implementation of PATR-II. In Research on interactive acquisition and use of knowledge, pages 39–79, SRI International, Menlo Park, CA, 1983.Google Scholar

Copyright information

© Springer Science+Business Media New York 1991

Authors and Affiliations

  • Norbert Reithinger

There are no affiliations available

Personalised recommendations