From Speech and Gestures to Dialogue Acts

  • Maciej Karpinski
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 5398)


In the present paper, selected problems related to the annotation of the DiaGest corpus are discussed. A system of dialogue acts is proposed along with a conceptual framework that allows for independent labelling of the contributions provided by various modalities and channels. Both auditory and visual modalities are considered. Four channels are defined as major ways of providing quasi-independent modal contributions. A four-dimensional categorisation of dialogue acts is proposed. It includes a separate dimension for attitude-related tags. Dialogue acts are conceptualised as multidimensional entities built on the basis of modal contributions provided by respective channels.


dialogue act multidimensionality multimodality annotation 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Traum, D.R.: 20 Questions for Dialogue Act Taxonomies. Journal of Semantics 17(1), 7–30 (2000)CrossRefGoogle Scholar
  2. 2.
    Bunt, H.: Dimensions in dialogue act annotation. In: Proceedings of the Fifth International Conference on Language Resources and Evaluation LREC 2006 (2006)Google Scholar
  3. 3.
    Core, M.G., Allen, J.F.: Coding Dialogues with the DAMSL Annotation Scheme. In: Traum, D. (ed.) Working Notes of the Fall Symposium in Communicative Action in Humans and Machines, pp. 28–35. AAAI, Menlo Park (1997)Google Scholar
  4. 4.
    Popescu-Belis, A.: Dimensionality of Dialogue Act Tagsets: An Empirical Analysis of Large Corpora. Language Resources and Evaluation 42(1), 99–107 (2008)CrossRefGoogle Scholar
  5. 5.
    Klein, M.: Standardisation Efforts on the Level of Dialogue Act in the MATE Project. In: Towards Standards and Tools for Discourse Tagging: Proceedings of the Workshop (1999)Google Scholar
  6. 6.
    Bunt, H.: Dialogue pragmatics and context specifcation. In: Bunt, H., Black, W. (eds.) Abduction, Belief and Context in Dialogue. Studies in Computational Pragmatics, pp. 81–150. John Benjamins, Amsterdam (2000)CrossRefGoogle Scholar
  7. 7.
    Bunt, H., Girard, Y.: Designing an Open, Multidimensional Dialogue Act Taxonomy. In: The Proceedings of DIALOR 2005 Workshop, Nancy (2005)Google Scholar
  8. 8.
    Popescu-Belis, A.: Normalizing dialogue act tagsets: how to keep ISO standards general. 6th ACL-SIGSEM & ISO TC37/SC4/TDG3 Meeting on Multimodal Semantic Representation, Tilburg, The Netherlands (invited talk) (2007)Google Scholar
  9. 9.
    Jarmolowicz, E., Karpinski, M., Malisz, Z., Szczyszek, M.: Gesture, Prosody and Lexicon in Task-oriented Dialogues: Multimedia Corpus Recording and Labelling. In: Esposito, A., Faundez-Zanuy, M., Keller, E., Marinaro, M. (eds.) COST Action 2102. LNCS (LNAI), vol. 4775, pp. 99–110. Springer, Heidelberg (2007)CrossRefGoogle Scholar
  10. 10.
    Clark, H.H., Schaefer, E.F.: Contributing to discourse. Cognitive Science 13, 259–294 (1989)CrossRefGoogle Scholar
  11. 11.
    Bunt, H., Morante, R., Keizer, S.: An empirically based computational model of grounding in dialogue. In: Proceedings of the 8th SIGdial Workshop on Discourse and Dialogue, Antwerp, Association for Computational Linguistics, pp. 283–290 (2007)Google Scholar
  12. 12.
    Pratkanis, A.R., Breckler, S.J., Greenwald, A.G. (eds.): Attitude Structure and Function. Lawrence Erlbaum, Mahwah (1989)Google Scholar
  13. 13.
    Fox, A.: Prosodic Features and Prosodic Structures: The Phonology of Suprasegmentals. OUP, Oxford (2000)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2009

Authors and Affiliations

  • Maciej Karpinski
    • 1
  1. 1.Institute of Linguistics & Center for Speech and Language ProcessingAdam Mickiewicz UniversityPoznanPoland

Personalised recommendations