Advertisement

International Journal of Speech Technology

, Volume 7, Issue 1, pp 45–54 | Cite as

Introducing Syntax Information in a Stochastically-Based Semantic Case Grammar Parser

  • Wolfgang Minker
Article
  • 38 Downloads

Abstract

We study the impact of introducing syntax information into a stochastic component for natural language understanding that is based on a purely semantic case grammar formalism. The parser operates in an application for train travel information retrieval, the French ARISE (Automatic Railway Information Systems for Europe) task. This application supports the development of schedule inquiry services by telephone. The semantic case grammar has been chosen in order to enhance robustness facing spontaneous speech effects. However, this robustness is likely to turn into a drawback, if the semantic analysis ignores information that is propagated by syntactic relations. Introducing additional syntax information, whose complexity is well adapted to the size of the stochastic model, may disambiguate and therefore improve the decoding.

attribute-value pairs data labeling Hidden Markov Models robustness semantic frame spontaneous human-machine interaction 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. Aust, H. and Oerder, M. (1994). Database query generation from spoken sentences. Interactive Voice Technology for Telecommunications Applications, IVTTA, pp. 141-144.Google Scholar
  2. Aust, H. and Oerder, M. (1995). Dialogue control in automatic inquiry systems. Proceedings of ESCA Workshop on Spoken Dialogue Systems, pp. 121-124.Google Scholar
  3. Aust, H., Oerder, M., and Seide, F. (1994). Experience with an automatic train timetable information system. Interactive Voice Technology for Telecommunications Applications, IVTTA, pp. 67-72.Google Scholar
  4. Bennacef, S.K. (1995). Modélisation du dialogue oral Homme-Machine-Mise en oeuvre dans une application de demande d'informations. Thèse de doctorat, Université de Paris XI, Orsay.Google Scholar
  5. Bennacef, S.K., Bonneau-Maynard, H., Gauvain, J.L., Lamel, L.F., and Minker,W. (1994).Aspoken language system For information retrieval. Proceedings of International Conference of Speech and Language Processing, ICSLP, pp. 1271-1274.Google Scholar
  6. Blasband, M. (1998). Speech Recognition in Practice: The ARISE Project. La Lettre de l'IA, pp. 207-210.Google Scholar
  7. Bod, R. (1999). Context-sensitive spoken dialogue processing with the DOP model. Natural Language Engineering, 5:309–323.Google Scholar
  8. Bruce, B. (1975). Case systems for natural language. Artificial Intelligence, 6:327–360.Google Scholar
  9. Burton, R. (1976). Semantic Grammar. An Engineering Technique for Constructing Natural Language Understanding Systems. BBN, Cambridge, Massachusetts. Rapport technique no. 3353.Google Scholar
  10. Constant, P. (1991). Analyse Syntaxique par Couches. Thèse de doctorat, École Nationale Supérieure des Télécommunications, Paris.Google Scholar
  11. Fillmore, Ch. J. (1968). The case for case. In Emmon Bach and Robert T. Harms (Eds.) Universals in Linguistic Theory. Holt and Rinehart and Winston Inc., pp. 1-90.Google Scholar
  12. Gauvain, J.L., Bennacef, S., Devillers, L., Lamel, L., and Rosset, S. (1997). Spoken language component of the MASK Kiosk. In K. Varghese and S. Pfleger (Eds.) Human Comfort & Security of Information Systems. Springer-Verlag, pp. 93-103.Google Scholar
  13. Good, I.J. (1953). The population of species and the estimation of population parameters. Biometrika, 40:237–264.Google Scholar
  14. Hayes, P., Hauptman, A., Carbonnell, J., and Tomita, M. (1986). Parsing spoken language, a semantic caseframe approach. Proceedings of Conference on Computational Linguistics, COLING, pp. 587-592.Google Scholar
  15. Issar, S. andWard,W. (1993).CMU's Robust spoken language understanding system. Proceedings of European Conference on Speech Technology, EUROSPEECH, pp. 2147-2150.Google Scholar
  16. 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.Google Scholar
  17. Lamel, L.F., Rosset, S., Gauvain, J.L., Bennacef, S.K., Garnier-Rizet, M., and Prouts, B. (1998). The LIMSI ARISE System. Interactive Voice Technology for Telecommunications Applications, IVTTA, pp. 209-214.Google Scholar
  18. Lamel, L.F., Bennacef, S.K., Bonneau-Maynard, H., Rosset, S., and Gauvain, J.L., (1995). Recent developments in spoken language systems for information retrieval. Proceedings of ESCA Workshop on Spoken Dialogue Systems, pp. 17-20.Google Scholar
  19. Levin, E. and Pieraccini, R. (1995). CHRONUS-The next generation. Proceedings of ARPA Workshop on Spoken Language Technology, pp. 269-271.Google Scholar
  20. Magerman, D. (1995). Statistical decision tree models for parsing. Proceedings of 33th Annual Meeting of the Association of Computational Linguistics, ACL, pp. 267-283.Google Scholar
  21. Miller, S., Bates, M., Bobrow, R., Ingria, R., Makhoul, J., and Schwartz, R. (1994). Recent progress in hidden understanding models. Proceedings of ARPA Workshop on Spoken Language Technology, pp. 276-280.Google Scholar
  22. Minker, W. (1997). Stochastically-based natural language understanding across tasks and languages. Proceedings of European Conference on Speech Technology, EUROSPEECH, pp. 1423-1426.Google Scholar
  23. Minker, W. (1998). Stochastic versus rule-based speech understanding for information retrieval. Speech Communication, 25(4):223–247.Google Scholar
  24. Minker, W. (1999a). Compréhension de la Parole Spontanée. L'Harmattan.Google Scholar
  25. Minker, W. (1999b). Design considerations for knowledge source representations of a stochastically-based natural language understanding component. Speech Communication, 28(2):141–154.Google Scholar
  26. Minker, W., Bennacef, S.K., and Gauvain, J.L. (1996). A stochastic case frame approach for natural language understanding. Proceedings of International Conference of Speech and Language Processing, ICSLP, pp. 1013-1016.Google Scholar
  27. 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
  28. Rosenfeld, R. (1995). The CMU Statistical Language Modeling Toolkit, and its use in the 1994 ARPA CSR Evaluation. Proceedings of ARPA Workshop on Spoken Language Technology, pp. 47-50.Google Scholar
  29. Schwartz, R., Miller, S., Stallard, D., and Makhoul, J. (1996). Language understanding using hidden understanding models. Proceedings of International Conference of Speech and Language Processing, ICSLP, pp. 997-1000.Google Scholar

Copyright information

© Kluwer Academic Publishers 2004

Authors and Affiliations

  • Wolfgang Minker
    • 1
  1. 1.Department of Information TechnologyUniversity of UlmUlm/DonauGermany

Personalised recommendations