Advertisement

Table of contents

  1. Front Matter
    Pages i-vii
  2. Hamidreza Chinaei, Brahim Chaib-draa
    Pages 1-6
  3. Hamidreza Chinaei, Brahim Chaib-draa
    Pages 7-19
  4. Hamidreza Chinaei, Brahim Chaib-draa
    Pages 21-43
  5. Hamidreza Chinaei, Brahim Chaib-draa
    Pages 45-65
  6. Hamidreza Chinaei, Brahim Chaib-draa
    Pages 67-88
  7. Hamidreza Chinaei, Brahim Chaib-draa
    Pages 89-107
  8. Hamidreza Chinaei, Brahim Chaib-draa
    Pages 109-112
  9. Back Matter
    Pages 113-119

About this book

Introduction

This book discusses the Partially Observable Markov Decision Process (POMDP) framework applied in dialogue systems. It presents POMDP as a formal framework to represent uncertainty explicitly while supporting automated policy solving. The authors propose and implement an end-to-end learning approach for dialogue POMDP model components. Starting from scratch, they present the state, the transition model, the observation model and then finally the reward model from unannotated and noisy dialogues. These altogether form a significant set of contributions that can potentially inspire substantial further work. This concise manuscript is written in a simple language, full of illustrative examples, figures, and tables.
  • Provides insights on building dialogue systems to be applied in real domain
  • Illustrates learning dialogue POMDP model components from unannotated dialogues in a concise format
  • Introduces an end-to-end approach that makes use of unannotated and noisy dialogue for learning each component of dialogue POMDPs

Keywords

Adaptive spoken dialogue systems Dialogue POMDP model POMDP for unannotated and noisy dialogues POMDP model learning Partially observable Markov decision process (POMDP) framework Speech and language processing Spoken dialogue management

Authors and affiliations

  • Hamidreza Chinaei
    • 1
  • Brahim Chaib-draa
    • 2
  1. 1.Dept of Comp Science, Apt 407University of TorontoTorontoCanada
  2. 2.Comp Sci & Software EngUniversité LavalQuebecCanada

Bibliographic information

  • DOI https://doi.org/10.1007/978-3-319-26200-0
  • Copyright Information The Authors 2016
  • Publisher Name Springer, Cham
  • eBook Packages Engineering
  • Print ISBN 978-3-319-26198-0
  • Online ISBN 978-3-319-26200-0
  • Series Print ISSN 2191-8112
  • Series Online ISSN 2191-8120
  • Buy this book on publisher's site
Industry Sectors
Pharma
Automotive
Biotechnology
Finance, Business & Banking
Electronics
IT & Software
Telecommunications
Consumer Packaged Goods
Aerospace
Oil, Gas & Geosciences
Engineering