The performance of an incremental generation component for multi-modal dialog contributions

  • Norbert Reithinger
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 587)


In this paper, the performance of POPEL is demonstrated, an incremental and parallel natural language generation component for written German dialog contributions. The system's architectural approach is based on a cascaded model with feedback. It provides the flexibility essential for the integration into a dialog system. Furthermore, this architecture enables the seamless addition of the generation of multi-modal output to the decision flow of the generator. The rule-based gesture generator follows the simulation-oriented approach that mimics natural pointing gestures on a graphic. The analysis of the generation of a short text consisting of two sentences in different discourse contexts demonstrates POPEL's contextdependent mode of generation.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. J. Allgayer and C. Reddig. What KL-ONE lookalikes need to cope with natural language. In: K. Bläsius, U. Hedstück, and C.R. Rollinger. Sorts and Types in Artificial Intelligence. Springer (1990) 240–285Google Scholar
  2. J. Allgayer, R.M. Jansen-Winkeln, C. Reddig, and N. Reithinger. Bidirectional use of knowledge in the multi-modal NL access system XTRA. 11. IJCAI Detroit (1989) 1492–1497Google Scholar
  3. R. Dale. Generating Referring Expressions in a Domain of Objects and Processes. PhD thesis. Department of Artificial Intelligence, University of Edinburgh (1988)Google Scholar
  4. K. DeSmedt and G. Kempen. The Representation of Grammatical Knowledge in a Model for Incremental Sentence Generation. In: C.L. Paris, W.R. Swartout, and W.C. Mann. Natural Language Generation in Artificial Intelligence and Computational Linguistics. Kluwer (1991) 329–349Google Scholar
  5. W. Finkler and G. Neumann. POPEL-HOW — a distributed parallel model for incremental natural language production with feedback. 11. IJCAI Detroit (1989) 1518–1523Google Scholar
  6. R.M. Jansen-Winkeln, A. Ndiaye, and N. Reithinger. FSS-WASTL — interactive knowledge acquisition for a semantic lexicon. In: E. Ardizzone, S. Gaglio, and F. Sorbello. Trends in Artificial Intelligence, 2nd AI*IA Congress. Palermo (1991) 108–116Google Scholar
  7. A. Jameson and W. Wahlster. User Modeling in Anaphora Generation: Ellipsis and Definite Description. 6. ECAI Orsay (1982) 222–227Google Scholar
  8. J. Jung, A. Kresse, N. Reithinger, and R. Schäfer. Das System ZORA — wissensbasierte Generierung von Zeigegesten. 13. GWAI Berlin (1989) 190–194Google Scholar
  9. A. Kobsa. The SB-ONE representation workbench. In: Proc. of the workshop on formal aspects of semantic networks. Santa Catalina Island, CA. (1989)Google Scholar
  10. A. Kobsa. Modeling the User's Conceptual Knowledge in BGP-MS, a User Modeling Shell System. Computational Intelligence 6 4 (1990)Google Scholar
  11. G. Lakoff. Women, Fire, and Dangerous Things. Chicago University Press (1987)Google Scholar
  12. W.C. Mann and S.A. Thompson. Rhetorical structure theory: A theory of text organisation. Technical Report ISI/RS-87-190. Information Sciences Institute, Marina del Rey (1987)Google Scholar
  13. J.D. Moore. A Reactive Approach to Explanation. PhD thesis. Computer Science Department, University of California, Los Angeles (1989)Google Scholar
  14. G. Neumann. A Bidirectional Model for Natural Language Processing. 5. EACL Berlin (1991) 245–250Google Scholar
  15. G. Neumann and W. Finkler. A head-driven approach to incremental and parallel generation of syntactic structures. 13. COLING Helsinki (1990) 288–293Google Scholar
  16. R. Reichman. Getting Computers to Talk Like You and Me. MIT Press (1985)Google Scholar
  17. N. Reithinger. Eine parallele Architektur zur inkrementellen Generierung multimodaler Dialogbeiträge. Infix Verlag, St. Augustin (1992)Google Scholar
  18. N. Reithinger. POPEL — an incremental and parallel natural language generation system. In: C.L. Paris, W.R. Swartout, and W.C. Mann. Natural Language Generation in Artificial Intelligence and Computational Linguistics. Kluwer (1991) 179–200Google Scholar
  19. D. Schmauks. Deixis in der Mensch-Maschine Interaktion. Niemeyer (1991)Google Scholar
  20. D. Schmauks and N. Reithinger. Generating multimodal output — conditions, advantages and problems. 12. COLING Budapest (1988) 584–588Google Scholar
  21. D. Schmauks and M. Wille. Simulation of communicative hand movements in human-computer-interaction. Computers and the Humanities 25 (1991) 129–140Google Scholar
  22. 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, SRI International Menlo Park, CA. (1983). 39–79Google Scholar
  23. N. Ward. A Flexible, Parallel Model of Natural Language Generation. PhD thesis. Computer Science Department, University of California Berkeley (1991)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1992

Authors and Affiliations

  • Norbert Reithinger
    • 1
  1. 1.SFB 314 -FB 14 Informatik IVUniversität des SaarlandesSaarbrücken 11Germany

Personalised recommendations