Adaptivity and Response Generation in a Spoken Dialogue System

  • Kristiina Jokinen
  • Graham Wilcock
Part of the Text, Speech and Language Technology book series (TLTB, volume 22)


The paper addresses the issue of how to increase adaptivity in response generation for a spoken dialogue system. Realization strategies for dialogue responses depend on communicative confidence levels and interaction management goals. We first describe a Java/XML-based generator which produces different realizations of system responses based on agendas specified by the dialogue manager. We then discuss how greater adaptivity can be achieved by using a set of distinct generator agents, each of which is specialized in its realization strategy (e.g. highly elliptical or highly explicit). This allows a simpler design of each generator agent, while increasing the overall system adaptivity to meet the requirements for flexible cooperation in incremental and immediate interactive situations.


Generator Agent Dialogue System Realization Strategy Natural Language Generation Dialogue Manager 
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. Allwood, J. (1976). Linguistic Communication as Action and Cooperation. Department of Linguistics, University of Geteborg. Gothenburg Monographs in Linguistics 2.Google Scholar
  2. Apache XML Project (2001). Xalan-Java. Scholar
  3. Carlson, L. (1988). Questions of identity in discourse. In Meyer, M., editor, Questions and Questioning, pages 144–181. Walter de Gruyter, Berlin.Google Scholar
  4. Cawsey, A. (2000). Presenting tailored resource descriptions: Will XSLT do the job? In 9th International World Wide Web Conference.
  5. Chafe, W. (1976). Givenness, contrastiveness, definiteness, subjects, and topics. In Li, C., editor, Subject and Topic. Academic Press.Google Scholar
  6. Danieli, M. and Gerbino, E. (1995). Metrics for evaluating dialogue strategies in a spoken language system. In Proceedings of the AAAI Spring Symposium on Empirical Methods in Discourse Interpretation and Generation, pages 34–39.Google Scholar
  7. Deemter, K. v., Krahraer, E., and Theune, M. (1999). Plan-based vs. template-based NLG: A false opposition? In Becker and Busemann (1999), pages 1–5.Google Scholar
  8. Jokinen, K. (2000). Learning dialogue systems. In Dybkjaer, L., editor, LREC 2000 Workshop: From Spoken Dialogue to Full Natural Interactive Dialogue — Theory, Empirical Analysis and Evaluation, pages 13–17, Athens.Google Scholar
  9. Jokinen, K. (2001). The Interact project. Elsnews, 10.2:10.Google Scholar
  10. Jokinen, K., Hurtig, T., Kevin Hynna, Kanto, K., Kaipainen, M., and Kerminen, A. (2001). Self-organizing dialogue management. In Proceedings of 2nd Workshop on NLP and Neural Networks, NLPRS-2001, Tokyo.Google Scholar
  11. Jokinen, K., Tanaka, H., and Yokoo, A. (1998). Planning dialogue contributions with new information. In Proceedings of the Ninth International Workshop on Natural Language Generation, pages 158–167, Niagara-on-the-Lake, Ontario.Google Scholar
  12. Kume, M., Sato, G. K., and Yoshimoto, K. (1989). A descriptive framework for translating speaker’s meaning: Towards a dialogue translation system between Japanese and English. In Fourth Conference of the European Chapter of the Association for Computational Linguistics, pages 264–271, Manchester.Google Scholar
  13. Kuppevelt, J. v. (1991). Topic en Comment. Expliciete en Impliciete Vraagstelling in Discourse. PhD thesis, University of Nijmegen.Google Scholar
  14. Litman, D. and Pan, S. (2000). Predicting and adapting to poor speech recognition in a spoken dialogue system. In Proceedings of the Seventeenth National Conference on Artificial Intelligence (AAAI-2000), pages 722–728, Austin, TX.Google Scholar
  15. Moore, J. (1995). Participating in Explanatory Dialogues. MIT Press.Google Scholar
  16. Reiter, E. and Dale, R. (2000). Building Natural Language Generation Systems. Cambridge University Press.Google Scholar
  17. Theune, M. (2000). From Data to Speech: Language Generation in Context. PhD thesis, Eindhoven University of Technology.Google Scholar
  18. Traum, D. and Allen, J. F. (1994). Discourse obligations in dialogue processing. In 32nd Annual Meeting of the Association for Computational Linguistics, pages 1–8, Las Cruces.Google Scholar
  19. Turunen, M. and Hakulinen, J. (2000). Jaspis — a framework for multilingual adaptive speech applications. In Proceedings of 6th International Conference on Spoken Language Processing, Beijing.Google Scholar
  20. VoiceXML Forum (2000). Voice extensible Markup Language VoiceXML, Version 1.00. Scholar
  21. Walker, M., Litman, D., Kamm, C., and Abella, A. (1998). Evaluating spoken dialogue agents with PARADISE: Two case studies. Computer Speech and Language, 12–3.Google Scholar
  22. Wilcock, G. (2001). Pipelines, templates and transformations: XML for natural language generation. In Proceedings of the 1st NLP and XML Workshop, pages 1–8, Tokyo.Google Scholar
  23. Wilcock, G. and Jokinen, K. (2001). Design of a generation component for a spoken dialogue system. In Proceedings of the 6th Natural Language Processing Pacific Rim Symposium (NLPRS-2001), pages 545–550, Tokyo.Google Scholar

Copyright information

© Springer Science+Business Media Dordrecht 2003

Authors and Affiliations

  • Kristiina Jokinen
    • 1
  • Graham Wilcock
    • 2
  1. 1.University of Art and Design HelsinkiHelsinkiFinland
  2. 2.University of HelsinkiHelsinkiFinland

Personalised recommendations