Advertisement

Convolutional Neural Networks for Multi-topic Dialog State Tracking

  • Hongjie ShiEmail author
  • Takashi Ushio
  • Mitsuru Endo
  • Katsuyoshi Yamagami
  • Noriaki Horii
Chapter
Part of the Lecture Notes in Electrical Engineering book series (LNEE, volume 427)

Abstract

The main task of the fourth Dialog State Tracking Challenge (DSTC4) is to track the dialog state by filling in various slots, each of which represents a major subject discussed in the dialog. In this article we focus on the ‘INFO’ slot that tracks the general information provided in a sub-dialog segment, and propose an approach for this slot-filling using convolutional neural networks (CNNs). Our CNN model is adapted to multi-topic dialog by including a convolutional layer with general and topic-specific filters. The evaluation on DSTC4 common test data shows that our approach outperforms all other submitted entries in terms of overall accuracy of the ‘INFO’ slot.

Keywords

Dialog state tracking Convolutional neural networks Multi-topic dialog state tracking Domain adaptation Semi-supervised learning 

References

  1. 1.
    Lemon, O., Pietquin, O.: Data-Driven Methods for Adaptive Spoken Dialogue Systems. Springer (2012)Google Scholar
  2. 2.
    Kim, S., D’Haro, L.F., Banchs, R.E., Williams, J.D., Henderson, M.: The fourth dialog state tracking challenge. In: Proceedings of the 7th International Workshop on Spoken Dialogue Systems (IWSDS) (2016)Google Scholar
  3. 3.
    Kim, Y.: Convolutional neural networks for sentence classification. arXiv preprint arXiv:1408.5882 (2014)
  4. 4.
    Daumé III, H.: Frustratingly easy domain adaptation. arXiv preprint arXiv:0907.1815 (2009)
  5. 5.
    Williams, J.: Multi-domain learning and generalization in dialog state tracking. In: Proceedings of SIGDIAL (2013)Google Scholar
  6. 6.
    Pan, S.J., Yang, Q.: IEEE Trans. Surv. Transfer Learn. 22(10), 1345–1359 (2010)Google Scholar
  7. 7.
    Mrkšić, N., Séaghdha, D.O., Thomson, B., Gašić, M., Su, P.H., Vandyke, D.: Multi-domain dialog state tracking using recurrent neural networks. In: Proceedings of SIGDIAL (2013)Google Scholar
  8. 8.
    Mikolov, T., Sutskever, I., Chen, K., Corrado, G.S., Dean, J.: Distributed representations of words and phrases and their compositionality. Adv. Neural Inf. Process. Syst. 3111–3119 (2013)Google Scholar
  9. 9.
    Zhang, Y., Wallace, B.: A sensitivity analysis of (and practitioners’ guide to) convolutional neural networks for sentence classification. arXiv preprint arXiv:1510.03820 (2015)
  10. 10.
    Hinton, G.E., Srivastava, N., Krizhevsky, A., Sutskever, I., Salakhutdinov, R.R.: Improving neural networks by preventing co-adaptation of feature detectors. arXiv preprint arXiv:1207.0580 (2012)
  11. 11.
    Tieleman, T., Hinton, G.E.: Lecture 6.5-rmsprop: Divide the gradient by a running average of its recent magnitude. COURSERA Neural Netw. Mach. Learn. 4 (2012)Google Scholar
  12. 12.
    Yarowsky, D.: Unsupervised word sense disambiguation rivaling supervised methods. In: Proceedings of the 33rd annual meeting on Association for Computational Linguistics, pp. 189–196 (1995)Google Scholar

Copyright information

© Springer Science+Business Media Singapore 2017

Authors and Affiliations

  • Hongjie Shi
    • 1
    Email author
  • Takashi Ushio
    • 1
  • Mitsuru Endo
    • 1
  • Katsuyoshi Yamagami
    • 1
  • Noriaki Horii
    • 1
  1. 1.Intelligence Research Laboratory, Panasonic CorporationOsakaJapan

Personalised recommendations