Data-Driven Methods for Adaptive Spoken Dialogue Systems

Computational Learning for Conversational Interfaces

  • Oliver Lemon
  • Olivier Pietquin

Table of contents

  1. Front Matter
    Pages i-ix
  2. Oliver Lemon
    Pages 1-4
  3. Verena Rieser, Oliver Lemon
    Pages 5-17
  4. James Henderson, Filip Jurčíček
    Pages 19-38
  5. Simon Keizer, Stéphane Rossignol, Senthilkumar Chandramohan, Olivier Pietquin
    Pages 39-73
  6. Milica Gašić, Filip Jurčíček, Blaise Thomson, Steve Young
    Pages 75-101
  7. Oliver Lemon, Srini Janarthanam, Verena Rieser
    Pages 103-130
  8. Roberto Pieraccini, David Suendermann
    Pages 151-171
  9. Olivier Pietquin
    Pages 173-177

About this book

Introduction

The EC FP7 project “Computational Learning in Adaptive Systems for Spoken Conversation” (CLASSiC) was a European initiative working on a fully data-driven architecture for the development of conversational interfaces, as well as new machine learning approaches for their sub-components. It developed a variety of novel statistical methods for spoken dialogue processing, for extended conversational interaction, which are now collected together in this book. A major focus of the project was in tracking the accumulation of information about user goals over multiple dialogue turns (i.e.\ extended conversational interaction), and in maintaining overall system robustness even when speech recognition results contain errors, by managing uncertainty through the processing chain.

Other advances were made in the areas of adaptive natural language generation (NLG), statistical methods for spoken language understanding (SLU), and machine learning methods for system optimisation, either during online operation, simulation, or from small amounts of data.

This book collects together the main research results and lessons learned in the CLASSiC project. Each chapter provides a summary of the specific methods developed and results obtained in its particular research area. In addition, leading researchers in statistical methods applied to industrial-scale dialogue systems (from SpeechCycle) have contributed a chapter surveying their recent work.

This volume will serve as a valuable introduction to the current state-of-the-art in statistical approaches to developing conversational interfaces, for active researchers in the field in industry and academia, as well as for students who are considering working in this exciting area.

Keywords

Adaptive user interfaces Machine Learning Spoken Dialogue Systems User Simulation

Editors and affiliations

  • Oliver Lemon
    • 1
  • Olivier Pietquin
    • 2
  1. 1., Mathematics and Computer ScienceHeriot Watt UniversityEdinburghUnited Kingdom
  2. 2., Metz Campus - IMS Research GroupSUPELECMetzFrance

Bibliographic information

  • DOI https://doi.org/10.1007/978-1-4614-4803-7
  • Copyright Information Springer Science+Business Media New York 2012
  • Publisher Name Springer, New York, NY
  • eBook Packages Computer Science
  • Print ISBN 978-1-4614-4802-0
  • Online ISBN 978-1-4614-4803-7
  • About this book