Towards Interrogative Types in Task-Oriented Dialogue Systems

  • Markus M. Berg
  • Antje Düsterhöft
  • Bernhard Thalheim
Part of the Lecture Notes in Computer Science book series (LNCS, volume 7337)

Abstract

The classification of questions and the identification of their respective answer types are crucial for different parts of a dialogue system and especially important for Rapid Application Development purposes. A common taxonomy of question types helps to connect parsers, grammars, pattern-based language generation methods and the natural language understanding module. Thus, in this paper we will present an overview of different question types and propose an abstract question description.

References

  1. 1.
    Bunt, H., Alexandersson, J., et al.: Towards an ISO Standard for Dialogue Act Annotation. In: LREC (2010)Google Scholar
  2. 2.
    Eduard, H., Gerber, L.: et al.: Question Answering in Webclopedia. In: Proceedings of the Ninth Text Retrieval Conference, pp. 655–664 (2000)Google Scholar
  3. 3.
    Graesser, A., Rus, V., Cai, Z.: Question classification schemes. In: Workshop on the Question Generation Shared Task and Evaluation Challenge pp. 8–9 (2008)Google Scholar
  4. 4.
    Hirschman, L., Gaizauskas, R.: Natural language question answering: the view from here. Nat. Lang. Eng. 7, 275–300 (2001)CrossRefGoogle Scholar
  5. 5.
    Moldovan, D.I., et al.: LASSO: A Tool for Surfing the Answer Net. In: Text Retrieval Conference (1999)Google Scholar
  6. 6.
    Srihari, R., Li, W.: Information Extraction Supported Question Answering. In: Proceedings of the Eighth Text Retrieval Conference (TREC-8), pp. 185–196 (1999)Google Scholar
  7. 7.
    Stokhof, M., Groenendijk, J.: Handbook of Logic and Language, ch.19, p. 21. Elsevier Science B.V (1994)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2012

Authors and Affiliations

  • Markus M. Berg
    • 1
    • 2
  • Antje Düsterhöft
    • 2
  • Bernhard Thalheim
    • 1
  1. 1.University of KielGermany
  2. 2.University of WismarGermany

Personalised recommendations