Data-Driven Methods for Adaptive Spoken Dialogue Systems: Computational Learning for Conversational Interfaces - Tapa blanda

Acerca del autor

Oliver Lemon is a Reader and head of the Interaction Lab in the school of Mathematical and Computer Sciences at Heriot Watt University, Edinburgh. Dr. Lemon is currently serving as the Program Chair for SIGDial 2010 and as a member of the Program Committee of INLG 2010. He is also on the Editorial Board of the new journal "Dialogue & Discourse". Prof. Pietquin and Dr. Lemon were co-chairs of the special session "Machine learning for adaptivity in spoken dialogue systems" at the InterSpeech 2009 conference, which inspired the development of this book.

Olivier Pietquin is an Associate Professor at the Ecole Superieure d'Electricite (Supelec, France), where he founded and currently heads the "Information, Multimodality & Signal" (IMS) research group. He is an elected member of the IEEE Speech and Language Technical Committee. Prof. Pietquin has four patents and has been published in over 45 journal articles, edited books, and conference proceedings.

De la contraportada

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.