Text Based Dialog Act Classification for Multiparty Meetings

  • Matthias Zimmermann
  • Dilek Hakkani-Tür
  • Elizabeth Shriberg
  • Andreas Stolcke
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4299)


This paper evaluates the performance of various machine learning approaches and their combination for text based dialog act (DA) classification of meetings data. For this task, boosting and three other text based approaches previously described in the literature are used. To further improve the classification performance, three different combination schemes take into account the results of the individual classifiers. All classification methods are evaluated on the ICSI Meeting Corpus based on both reference transcripts and the output of a speech-to-text (STT) system. The results indicate that both the proposed boosting based approach and a method relying on maximum entropy substantially outperform the use of mini language models and a simple scheme relying on cue phrases. The best performance was achieved by combining individual methods with a multilayer perceptron.


Reference Condition Maximum Entropy Word Error Rate Maximum Entropy Modeling String Kernel 
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.
    Jurafsky, D., Martin, J.: Speech and Language Processing: An Introduction to Natural Language Processing. In: Computational Linguistics and Speech Recognition. Prentice Hall, Englewood Cliffs (2000)Google Scholar
  2. 2.
    Anderson, A., et al.: The HCRC map task corpus. Language and Speech 34(4), 351–366 (1991)Google Scholar
  3. 3.
    Reithinger, N., Klesen, M.: Dialog act classification using language models. In: Proc. ICASSP, Rhodes, Greece, vol. 3, pp. 2235–2238 (1997)Google Scholar
  4. 4.
    Core, M., Allen, J.: Coding dialogues with the DAMSL annotation scheme. In: AAAI Fall Symposium on Communicative Action in Humans and Machines, Cambridge, USA, pp. 28–35 (1997)Google Scholar
  5. 5.
    Shriberg, E., et al.: The ICSI meeting recorder dialog act (MRDA) corpus. In: Proc. SIGDIAL, Cambridge, USA, pp. 97–100 (2004)Google Scholar
  6. 6.
    Ang, J., Liu, Y., Shriberg, E.: Automatic dialog act segmentation and classification in multiparty meetings. In: Proc. ICASSP, Philadelphia, USA, vol. 1, pp. 1061–1064 (2005)Google Scholar
  7. 7.
    Zimmermann, M., Stolcke, A., Shriberg, E.: Joint segmentation and classification of dialog acts in multi-party meetings. In: Proc. 31st ICASSP, Toulouse, France, vol. 1, pp. 581–584 (2006)Google Scholar
  8. 8.
    Nagata, M., Morimoto, T.: First steps toward statistical modeling of dialogue to predict the speech act type of the next utterance. Speech Communication 15, 193–203 (1994)CrossRefGoogle Scholar
  9. 9.
    Warnke, V., Kompe, R., Niemann, H., Nöth, E.: Integrated dialog act segmentation and classification using prosodic features and language models. In: Proc. 5th Europ. Conf. on Speech, Communication, and Technology, Rhodes, Greece, vol. 1, pp. 207–210 (1997)Google Scholar
  10. 10.
    Stolcke, A., Ries, K., Coccaro, N., Shriberg, E., Bates, R., Jurafsky, D., Taylor, P., Martin, R., Ess-Dykema, C.V., Meteer, M.: Dialogue act modeling for automatic tagging and recognition of conversational speech. Computational Linguistics 26(3), 339–371 (2000)CrossRefGoogle Scholar
  11. 11.
    Mast, M., et al.: Dialog act classification with the help of prosody. In: Proc. ICSLP, Philadelphia, USA, vol. 3, pp. 1732–1735 (1996)Google Scholar
  12. 12.
    Samuel, K., Carberry, S., Vijay-Shanker, K.: Dialogue act tagging with transformation-based learning. In: Proc. 17th Int. Conference on Computational Linguisitics, Montreal, Canada, vol. 2, pp. 1150–1156 (1998)Google Scholar
  13. 13.
    Ries, K.: HMM and neural network based speech act detection. In: Proc. ICASSP, Phoenix, USA, vol. 1, pp. 497–500 (1999)Google Scholar
  14. 14.
    Ji, G., Bilmes, J.: Dialog act tagging using graphical models. In: Proc. ICASSP, Philadelphia, USA, vol. 1, pp. 33–36 (2005)Google Scholar
  15. 15.
    Webb, N., Hepple, M., Wilks, Y.: Dialog act classification based on intra-utterance features. CS-05-01, Dept. of Comp. Science, University of Sheffield, UK (2005)Google Scholar
  16. 16.
    Berger, A.L., Pietra, S.A.D., Pietra, V.J.D.: A maximum entropy approach to natural language processing. Computational Linguistics 22(1), 39–71 (1996)Google Scholar
  17. 17.
    Schapire, R.E., Singer, Y.: BoosTexter: A boosting-based system for text categorization. Machine Learning 39(2-3), 135–168 (2000)zbMATHCrossRefGoogle Scholar
  18. 18.
    Stolcke, A., Anguera, X., Boakye, K., Çetin, O., Grezl, F., Janin, A., Mandal, A., Peskin, B., Wooters, C., Zheng, J.: Further progress in meeting recognition: The icsi-sri spring 2005 speech-to-text evaluation system. In: Renals, S., Bengio, S. (eds.) MLMI 2005. LNCS, vol. 3869, pp. 463–475. Springer, Heidelberg (2006)CrossRefGoogle Scholar
  19. 19.
    Goodman, J.T.: A bit of progress in language modeling. MSR-TR-2001-72, Machine Learning and Applied Statistics Group, Microsoft, Redmond, USA (2001)Google Scholar
  20. 20.
    Leslie, C., Eskin, E., Noble, W.S.: The spectrum kernel: A string kernel for SVM protein classification. In: Proc. Pacific Symposium on Biocomputing, pp. 564–575 (2002)Google Scholar
  21. 21.
    Lodhi, H., Saunders, C., Shawe-Taylor, J., Cristianini, N., Watkins, C.: Text classification using string kernels. Journal of Machine Learning Research 2, 419–444 (2002)zbMATHCrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Matthias Zimmermann
    • 1
  • Dilek Hakkani-Tür
    • 1
  • Elizabeth Shriberg
    • 1
    • 2
  • Andreas Stolcke
    • 1
    • 2
  1. 1.International Computer Science Institute (ICSI)BerkeleyUSA
  2. 2.SRI InternationalMenlo ParkUSA

Personalised recommendations