Skip to main content

Advertisement

SpringerLink
Log in

Hidden Markov Modeling for Semantic Analysis—On the Combination of Different Decoding Strategies

  • Published:
International Journal of Speech Technology Aims and scope Submit manuscript

Abstract

Different strategies to enhance the semantic decoding accuracy of a stochastic parser are discussed and comparatively evaluated on a corpus containing dialogues between two persons scheduling a meeting. Using a stochastic parsing method the human effort can be limited to the task of data labeling, which is much simpler than the design, maintenance and extension of grammar rules, especially for non-experts. Since a stochastic method automatically learns the semantic formalism through an analysis of these data, it is comparatively flexible and robust and can easily be ported to different applications, domains and human languages. The performance of the parser was improved by subsequently adding valuable and removing redundant semantic information, as well as by combining several decoding methods either sequentially or in parallel.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Similar content being viewed by others

References

  • Clrkson, P.R. and Rosenfeld, R. (1999). The CMU-cambridge statistical language modeling toolkit v2. http://mi.eng.cam.ac.uk/∼prc14/toolkit.html.

  • He, Y. and Young, S. (2005). Semantic processing using the hidden vector state model. Computer Speech and Language, 19(1):85–106.

    Article  Google Scholar 

  • He, Y. and Young, S. (2003). Hidden vector state model for hierarchical semantic parsing. In Proceedings of International Conference on Acoustics, Speech and Signal Processing, pp. 268–271.

  • Katz, S.M. (1987). Estimation of probabilities from sparse data for the language model component of a speech recognizer. IEEE Transactions on Acoustics, Speech and Signal Processing, 35(3):400–401.

    Article  Google Scholar 

  • Lavie, A., Gates, D., Coccaro, N., and Levin, L. (1996). Input segmentation of spontaneous speech in JANUS: A speech-to-speech translation system. In Proceedings of ECAI Workshop on Dialogue Processing in Spoken Language Systems, pp. 86–99.

  • Levin, E. and Pieraccini, R. (1995). CHRONUS—The next generation. In Proceedings of ARPA Spoken Language Technology Workshop, pp. 269–271.

  • Luengo, I., Navas, E., Hernáez, I., and Sánchez, J. (2005). Automatic emotion recognition using prosodic parameters. In Proceedings of European Conference on Speech Communication and Technology (EUROSPEECH), pp. 493–496.

  • Mayfield, L., Gavaldà, M., Ward, W., and Waibel, A. (1995). Concept-based speech translation. In Proceedings of International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 97–100.

  • Minker, W. (1997). Stochastically-based natural language understanding across tasks and languages. In Proceedings of European Conference on Speech Communication and Technology (EUROSPEECH), pp. 1423–1426.

  • Minker, W., Waibel, A., and Mariani, J. (1999). Stochastically-Based Semantic Analysis of Spoken Natural Language. Boston, MA, USA, Kluwer Academic Publishers.

  • Minker, W., Gavaldà, M., and Waibel, A. (1999). Stochastically-based semantic analysis for machine translation. Computer Speech and Language, 13(2):177–194.

    Article  Google Scholar 

  • Levin, E., Pieraccini, R., and Eckert, W. (1998). Using Markov decision process for learning dialogue strategies. In Proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

  • Rabiner, L.R. and Juang, B.H. (1986). An introduction to Hidden Markov Models. IEEE Transactions on Acoustics, Speech and Signal Processing, 3(1):4–16.

    Google Scholar 

  • Schwartz, R., Miller, S., Stallard, D., and Makhoul, J. (1996). Language Understanding Using Hidden Understanding Models. In Proceedings of International Conference on Speech and Language Processing (ICSLP), pp. 997–1000.

  • Waibel, A. (1996). Interactive translation of conversational speech. Computer, 27(7):41–48.

    Article  Google Scholar 

  • Wang, Y.-Y. and Acero, A. (2003). Concept acquisition in example-based grammar authoring. In Proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing, pp. 284–287.

  • Ward, W. (1994). Extracting information in spontaneous speech. In Proceedings of International Conference on Speech and Language Processing (ICSLP), pp. 83–86.

  • Ward, W. (1991). Understanding spontaneous speech: The phoenix system. In Proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing, pp. 365–367.

Download references

Author information

Authors and Affiliations

  1. Department of Information Technology, University of Ulm, Germany

    Christiane Beuschel, Wolfgang Minker & Dirk Bühler

Authors
  1. Christiane Beuschel
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Wolfgang Minker
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Dirk Bühler
    View author publications

    You can also search for this author in PubMed Google Scholar

Rights and permissions

Reprints and permissions

About this article

Cite this article

Beuschel, C., Minker, W. & Bühler, D. Hidden Markov Modeling for Semantic Analysis—On the Combination of Different Decoding Strategies. Int J Speech Technol 8, 295–305 (2005). https://doi.org/10.1007/s10772-006-8733-7

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s10772-006-8733-7

Keywords

Search

Navigation