My Account Log in

1 option

Data-Driven Methods for Adaptive Spoken Dialogue Systems : Computational Learning for Conversational Interfaces / edited by Oliver Lemon, Olivier Pietquin.

SpringerLink Books Computer Science (2011-2024) Available online

View online
Format:
Book
Contributor:
Lemon, Oliver, editor.
Pietquin, Olivier, editor.
SpringerLink (Online service)
Series:
Computer Science (Springer-11645)
Language:
English
Subjects (All):
User interfaces (Computer systems).
Computational linguistics.
Signal processing.
Image processing.
Speech processing systems.
Computer simulation.
Computer arithmetic and logic units.
User Interfaces and Human Computer Interaction.
Computational Linguistics.
Signal, Image and Speech Processing.
Simulation and Modeling.
Arithmetic and Logic Structures.
Local Subjects:
User Interfaces and Human Computer Interaction.
Computational Linguistics.
Signal, Image and Speech Processing.
Simulation and Modeling.
Arithmetic and Logic Structures.
Physical Description:
1 online resource (X, 178 pages)
Edition:
First edition 2012.
Contained In:
Springer eBooks
Place of Publication:
New York, NY : Springer New York : Imprint: Springer, 2012.
System Details:
text file PDF
Summary:
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 (id est\ 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.
Contents:
Chapter 1. Conversational Interfaces
Chapter 2. Developing Dialogue Managers from Limited Amounts of Data
Chapter 3. Data-Driven Methods for Spoken Language Understanding
Chapter 4. User Simulation in the Development of Statistical Spoken Dialogue Systems
Chapter 5. Optimisation for POMDP-based Spoken Dialogue Systems
Chapter 6. Statistical Approaches to Adaptive Natural Language Generation
Chapter 7. Metrics and Evaluation of Spoken Dialogue Systems
Chapter 8. Data-Driven Methods in Industrial Spoken Dialog Systems
Chapter 9. Future Research Directions.
Other Format:
Printed edition:
ISBN:
978-1-4614-4803-7
9781461448037
Access Restriction:
Restricted for use by site license.

The Penn Libraries is committed to describing library materials using current, accurate, and responsible language. If you discover outdated or inaccurate language, please fill out this feedback form to report it and suggest alternative language.

Find

Home Release notes

My Account

Shelf Request an item Bookmarks Fines and fees Settings

Guides

Using the Find catalog Using Articles+ Using your account