Skip to main content

Learning Observation Models for Dialogue POMDPs

  • Conference paper

Part of the Lecture Notes in Computer Science book series (LNAI,volume 7310)

Abstract

The SmartWheeler project aims at developing an intelligent wheelchair for handicapped people. In this paper, we model the dialogue manager of SmartWheeler in MDP and POMDP frameworks using its collected dialogues. First, we learn the model components of the dialogue MDP based on our previous works. Then, we extend the dialogue MDP to a dialogue POMDP, by proposing two observation models learned from dialogues: one based on learned keywords and the other based on learned intentions. The subsequent keyword POMDP and intention POMDP are compared based on accumulated mean reward in simulation runs. Our experimental results show that the quality of the intention model is significantly higher than the keyword one.

This is a preview of subscription content, access via your institution.

Buying options

Chapter
USD   29.95
Price excludes VAT (USA)
  • DOI: 10.1007/978-3-642-30353-1_24
  • Chapter length: 7 pages
  • Instant PDF download
  • Readable on all devices
  • Own it forever
  • Exclusive offer for individuals only
  • Tax calculation will be finalised during checkout
eBook
USD   74.99
Price excludes VAT (USA)
  • ISBN: 978-3-642-30353-1
  • Instant PDF download
  • Readable on all devices
  • Own it forever
  • Exclusive offer for individuals only
  • Tax calculation will be finalised during checkout
Softcover Book
USD   99.00
Price excludes VAT (USA)

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. Blei, D.M., Ng, A.Y., Jordan, M.I.: Latent Dirichlet Allocation. Journal of Machine Learning Research 3, 993–1022 (2003)

    MATH  Google Scholar 

  2. Chinaei, H.R., Chaib-draa, B.: Learning Dialogue POMDP Models from Data. In: Butz, C., Lingras, P. (eds.) Canadian AI 2011. LNCS, vol. 6657, pp. 86–91. Springer, Heidelberg (2011)

    CrossRef  Google Scholar 

  3. Chinaei, H.R., Chaib-draa, B., Lamontagne, L.: Application of Hidden Topic Markov Models on Spoken Dialogue Systems. In: Filipe, J., Fred, A., Sharp, B. (eds.) ICAART 2009. CCIS, vol. 67, pp. 151–163. Springer, Heidelberg (2010)

    CrossRef  Google Scholar 

  4. Gruber, A., Rosen-Zvi, M., Weiss, Y.: Hidden Topic Markov Models. In: Artificial Intelligence and Statistics (AISTATS), San Juan, Puerto Rico (2007)

    Google Scholar 

  5. Pineau, J., Gordon, G., Thrun, S.: Point-based Value Iteration: An Anytime Algorithm for POMDPs. In: International Joint Conference on Artificial Intelligence (IJCAI), Acapulco, Mexico, pp. 1025–1032 (August 2003)

    Google Scholar 

  6. Pineau, J., West, R., Atrash, A., Villemure, J., Routhier, F.: On the Feasibility of Using a Standardized Test for Evaluating a Speech-Controlled Smart Wheelchair. International Journal of Intelligent Control and Systems 16(2), 124–131 (2011)

    Google Scholar 

  7. Williams, J.D., Young, S.: The SACTI-1 Corpus: Guide for Research Users. Cambridge University Department of Engineering. Technical report (2005)

    Google Scholar 

  8. Williams, J.D., Young, S.: Partially Observable Markov Decision Processes for Spoken Dialog Systems. Computer Speech and Language 21, 393–422 (2007)

    CrossRef  Google Scholar 

Download references

Author information

Authors and Affiliations

Authors

Editor information

Editors and Affiliations

Rights and permissions

Reprints and Permissions

Copyright information

© 2012 Springer-Verlag Berlin Heidelberg

About this paper

Cite this paper

Chinaei, H.R., Chaib-draa, B., Lamontagne, L. (2012). Learning Observation Models for Dialogue POMDPs. In: Kosseim, L., Inkpen, D. (eds) Advances in Artificial Intelligence. Canadian AI 2012. Lecture Notes in Computer Science(), vol 7310. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-30353-1_24

Download citation

  • DOI: https://doi.org/10.1007/978-3-642-30353-1_24

  • Publisher Name: Springer, Berlin, Heidelberg

  • Print ISBN: 978-3-642-30352-4

  • Online ISBN: 978-3-642-30353-1

  • eBook Packages: Computer ScienceComputer Science (R0)