Discriminative training of the hidden vector state model for semantic parsing

Article English OPEN
Zhou, Deyu ; He, Yulan (2009)

In this paper, we discuss how discriminative training can be applied to the hidden vector state (HVS) model in different task domains. The HVS model is a discrete hidden Markov model (HMM) in which each HMM state represents the state of a push-down automaton with a finite stack size. In previous applications, maximum-likelihood estimation (MLE) is used to derive the parameters of the HVS model. However, MLE makes a number of assumptions and unfortunately some of these assumptions do not hold. Discriminative training, without making such assumptions, can improve the performance of the HVS model by discriminating the correct hypothesis from the competing hypotheses. Experiments have been conducted in two domains: the travel domain for the semantic parsing task using the DARPA Communicator data and the Air Travel Information Services (ATIS) data and the bioinformatics domain for the information extraction task using the GENIA corpus. The results demonstrate modest improvements of the performance of the HVS model using discriminative training. In the travel domain, discriminative training of the HVS model gives a relative error reduction rate of 31 percent in F-measure when compared with MLE on the DARPA Communicator data and 9 percent on the ATIS data. In the bioinformatics domain, a relative error reduction rate of 4 percent in F-measure is achieved on the GENIA corpus.
  • References (34)
    34 references, page 1 of 4

    [1] J. Dowding, R. Moore, F. Andry, and D. Moran, “Interleaving syntax and semantics in an efficient bottom-up parser,” in Proc. of the 32th Annual Meeting of the Association for Computational Linguistics, Las Cruces, New Mexico, USA, 1994, pp. 110-116.

    [2] W. Ward and S. Issar, “Recent improvements in the cmu spoken language understanding system,” in Proc. of the workshop on Human Language Technology, Plainsboro, New Jerey, USA, 1994, pp. 213-216.

    [3] M. Collins, “Head-driven statistical models for natural language parsing,” Ph.D. dissertation, University of Pennsylvania, Philadelphia, PA, 1999.

    [4] E. Charniak, “A maximum entropy inspired parser,” in 1st Meeting of North American Chapter of Association for Computational Linguistics, Seattle, Washington, 2000, pp. 132-139.

    [5] Y. Normandin and S. D. Morgera, “An improved mmie training algorithm for speaker-independent, small vocabulary, continuous speech recognition,” in Acoustics, Speech, and Signal Processing, IEEE International Conference on ICASSP '91, 1991, pp. 537 - 540.

    [6] B. Juang, W. Chou, and C. Lee, “Statistical and discriminative methods for speech recognition,” in Speech Recognition and Understanding, ser. NATO ASI Series, Rubio, Ed. Berlin: Springer-Verlag, 1993.

    [7] W. Chou, C. Lee, and B. Juang, “Minimum error rate training based on n-best string models,” in Acoustics, Speech, and Signal Processing, IEEE International Conference on ICASSP '93, vol. 2, April 1993, pp. 652 - 655.

    [8] J. Chen and F. Soong, “An n-best candidates-based discriminative training for speech recognition applications,” IEEE Transactions on Speech and Audio Processing, vol. 2, pp. 206 - 216, 1994.

    [9] B. Juang, W. Hou, and C. Lee, “Minimum classification error rate methods for speech recognition,” IEEE Transactions on Speech and Audio Processing, vol. 5, pp. 257 - 265, 1997.

    [10] R. Pieraccini, E. Tzoukermann, Z. Gorelov, E. Levin, C. H. Lee, and J.-L. Gauvain., “Progress report on the chronus system: Atis benchmark results,” in Proc. of DARPA Speech and Natural Language Workshop, 1992, pp. 67-71.

  • Similar Research Results (6)
  • Metrics
    0
    views in OpenAIRE
    0
    views in local repository
    2
    downloads in local repository

    The information is available from the following content providers:

    From Number Of Views Number Of Downloads
    Aston Publications Explorer - IRUS-UK 0 2
Share - Bookmark