Skip to main content
    • Aa
    • Aa
  • Get access
    Check if you have access via personal or institutional login
  • Cited by 2
  • Cited by
    This article has been cited by the following publications. This list is generated based on data provided by CrossRef.

    Bridgers, Franca Ferrari and Kacinik, Natalie 2016. How Linearity and Structural Complexity Interact and Affect the Recognition of Italian Derived Words. Journal of Psycholinguistic Research,

    Brown, C. Hendricks Mohr, David C. Gallo, Carlos G. Mader, Christopher Palinkas, Lawrence Wingood, Gina Prado, Guillermo Kellam, Sheppard G. Pantin, Hilda Poduska, Jeanne Gibbons, Robert McManus, John Ogihara, Mitsunori Valente, Thomas Wulczyn, Fred Czaja, Sara Sutcliffe, Geoff Villamar, Juan and Jacobs, Christopher 2013. A Computational Future for Preventing HIV in Minority Communities. JAIDS Journal of Acquired Immune Deficiency Syndromes, Vol. 63, p. S72.


Estimating the number of segments for improving dialogue act labelling

  • DOI:
  • Published online: 14 February 2011

In dialogue systems it is important to label the dialogue turns with dialogue-related meaning. Each turn is usually divided into segments and these segments are labelled with dialogue acts (DAs). A DA is a representation of the functional role of the segment. Each segment is labelled with one DA, representing its role in the ongoing discourse. The sequence of DAs given a dialogue turn is used by the dialogue manager to understand the turn. Probabilistic models that perform DA labelling can be used on segmented or unsegmented turns. The last option is more likely for a practical dialogue system, but it provides poorer results. In that case, a hypothesis for the number of segments can be provided to improve the results. We propose some methods to estimate the probability of the number of segments based on the transcription of the turn. The new labelling model includes the estimation of the probability of the number of segments in the turn. We tested this new approach with two different dialogue corpora: SwitchBoard and Dihana. The results show that this inclusion significantly improves the labelling accuracy.

Linked references
Hide All

This list contains references from the content that can be linked to their source. For a full set of references and notes please see the PDF or HTML where available.

L. Dybkjaer and W. Minker 2008. Recent Trends in Discourse and Dialogue, vol. 39 of Text, Speech and Language Technology. Springer.

M. Fraser and G. Gilbert 1991. ‘Simulating speech systems.’ Computer Speech and Language (5): 81–9.

P. García and E. Vidal 1990. Inference of k-testable languages in the strict sense and application to syntactic pattern recognition. IEEE Transactions on Pattern Analysis Machine Intelligence 12 (9): 920–5. ISSN: 0162-8828. (1990), IEEE Computer Society.

A. Gorin , G. Riccardi and J. Wright 1997. How may I help you? Speech Communication 23: 113–27.

C. D. Martínez-Hinarejos , J. M. Benedí , and R. Granell 2008. Statistical framework for a Spanish spoken dialogue corpus. Speech Communication 50: 9921008.

C. D. Martínez-Hinarejos , R. Granell , and J. M. Benedí 2006. Segmented and unsegmented dialogue-act annotation with statistical dialogue models. In Proceedings of the COLING/ACL 2006 Main Conference Poster Sesions, Sydney, Australia, pp. 563–70.

A. Stolcke , N. Coccaro , R. Bates , P. Taylor , C. van Ess-Dykema , K. Ries , E. Shriberg , D. Jurafsky , R. Martin , and M. Meteer 2000. Dialogue act modelling for automatic tagging and recognition of conversational speech. Computational Linguistics 26 (3): 134.

S. Young 2000. Probabilistic methods in spoken dialogue systems. Philosophical Trans Royal Society (Series A) 358(1769): 1389–402.

Recommend this journal

Email your librarian or administrator to recommend adding this journal to your organisation's collection.

Natural Language Engineering
  • ISSN: 1351-3249
  • EISSN: 1469-8110
  • URL: /core/journals/natural-language-engineering
Please enter your name
Please enter a valid email address
Who would you like to send this to? *