Advertisement

Regularized Neural User Model for Goal-Oriented Spoken Dialogue Systems

  • Manex Serras
  • María Inés TorresEmail author
  • Arantza del Pozo
Chapter
Part of the Lecture Notes in Electrical Engineering book series (LNEE, volume 510)

Abstract

User simulation is widely used to generate artificial dialogues in order to train statistical spoken dialogue systems and perform evaluations. This paper presents a neural network approach for user modeling that exploits an encoder-decoder bidirectional architecture with a regularization layer for each dialogue act. In order to minimize the impact of data sparsity, the dialogue act space is compressed according to the user goal. Experiments on the Dialogue State Tracking Challenge 2 (DSTC2) dataset provide significant results at dialogue act and slot level predictions, outperforming previous neural user modeling approaches in terms of F1 score.

Keywords

User simulation Dialogue systems Deep learning Regularization 

Notes

Acknowledgements

This work has been partially funded by the Spanish Minister of Science under grants TIN2014-54288-C4-4-R and TIN2017-85854-C4-3-R and by the EU H2020 EMPATHIC project grant number 769872.

References

  1. 1.
    Asher N, Lascarides A (2001) Indirect speech acts. Synthese 128(1):183–228.  https://doi.org/10.1023/A:1010340508140
  2. 2.
    Chandramohan S, Geist M, Lefevre F, Pietquin O (2011) User simulation in dialogue systems using inverse reinforcement learning. Interspeech 2011:1025–1028Google Scholar
  3. 3.
    Cho K, van Merriënboer B, Bahdanau D, Bengio Y (2014) On the properties of neural machine translation: encoder–decoder approaches. Syntax Semant Struct Stat Transl, p 103Google Scholar
  4. 4.
    Core MG, Allen J (1997) Coding dialogs with the damsl annotation scheme. In: AAAI fall symposium on communicative action in humans and machines, Boston, MA, vol 56Google Scholar
  5. 5.
    Cuayáhuitl H, Renals S, Lemon O, Shimodaira H (2005) Human-computer dialogue simulation using hidden markov models. In: 2005 IEEE workshop on automatic speech recognition and understanding. IEEE, pp 290–295Google Scholar
  6. 6.
    Eckert W, Levin E, Pieraccini R (1997) User modeling for spoken dialogue system evaluation. In: Proceedings of the IEEE workshop on automatic speech recognition and understanding, 1997. IEEE, pp 80–87Google Scholar
  7. 7.
    Hancher M (1979) The classification of cooperative illocutionary acts. Lang Soc, pp 1–14Google Scholar
  8. 8.
    Henderson M, Thomson B, Williams J (2013) Dialog state tracking challenge 2 and 3 handbook. http://camdial.org/mh521/dstc
  9. 9.
    Hochreiter S, Schmidhuber J (1997) Long short-term memory. Neural Comput 9(8):1735–1780CrossRefGoogle Scholar
  10. 10.
    Hurtado LF, Griol D, Sanchis E, Segarra E (2007) A statistical user simulation technique for the improvement of a spoken dialog system. Springer, Berlin, pp 743–752.  https://doi.org/10.1007/978-3-540-76725-1_77
  11. 11.
    Kingma D, Ba J (2015) Adam: a method for stochastic optimization. In: Proceedings of the 3rd international conference on learning representations (ICLR), pp 1–13Google Scholar
  12. 12.
    Layla EA, Jing H, Suleman K (2016) A sequence-to-sequence model for user simulation in spoken dialogue systems. In: InterspeechGoogle Scholar
  13. 13.
    Levin E, Pieraccini R, Eckert W (2000) A stochastic model of human-machine interaction for learning dialog strategies. IEEE Trans Speech Audio Process 8(1):11–23CrossRefGoogle Scholar
  14. 14.
    Pietquin O (2005) A framework for unsupervised learning of dialogue strategies. Presses univ. de LouvainGoogle Scholar
  15. 15.
    Pietquin O, Dutoit T (2006) A probabilistic framework for dialog simulation and optimal strategy learning. IEEE Trans Audio Speech Lang Process 14(2):589–599CrossRefGoogle Scholar
  16. 16.
    Quarteroni S, González M, Riccardi G, Varges S (2010) Combining user intention and error modeling for statistical dialog simulators. In: INTERSPEECH, pp 3022–3025Google Scholar
  17. 17.
    Rieser V, Lemon O (2006) Cluster-based user simulations for learning dialogue strategies. In: InterspeechGoogle Scholar
  18. 18.
    Schatzmann J, Thomson B, Weilhammer K, Ye H, Young S (2007) Agenda-based user simulation for bootstrapping a pomdp dialogue system. In: Human language technologies 2007: the conference of the north american chapter of the association for computational linguistics; companion volume, Short Papers. Association for Computational Linguistics, pp 149–152Google Scholar
  19. 19.
    Schatzmann J, Weilhammer K, Stuttle M, Young S (2006) A survey of statistical user simulation techniques for reinforcement-learning of dialogue management strategies. Knowl Eng Rev 21(2):97–126CrossRefGoogle Scholar
  20. 20.
    Scheffler K, Young S (2000) Probabilistic simulation of human-machine dialogues. In: Proceedings of the 2000 IEEE international conference on acoustics, speech, and signal processing, 2000, ICASSP’00, vol 2. IEEE, pp II1217–II1220Google Scholar

Copyright information

© Springer International Publishing AG, part of Springer Nature 2019

Authors and Affiliations

  • Manex Serras
    • 1
  • María Inés Torres
    • 2
    Email author
  • Arantza del Pozo
    • 1
  1. 1.Speech and Natural Language Technologies, Vicomtech Research centreDonostia-San SebastianSpain
  2. 2.Speech Interactive Research GroupUniversidad del País Vasco UPV/EHULeioaSpain

Personalised recommendations