Einschränkung Ihrer Suchanfrage auf den Bestand einer Bibliothek
Festlegung des Sortierkriteriums der Treffermenge
Die unscharfe Suche berücksichtigt auch Schreibfehler oder -varianten bei Ihrer Suche!
* Suchen (und) = ein Suchauftrag mit 2 oder mehr Suchbegriffen findet Titel, die alle Suchbegriffe enthalten. * Suchen (oder) = ein Suchauftrag mit 2 oder mehr Suchbegriffen zeigt alle Titel, die mindestens einen der Suchbegriffe enthalten * Mit Index blättern erhalten Sie eine alphabetisch sortierte Liste aller Begriffe, die wie Ihr Suchbegriff beginnen. * Nach einem Suchauftrag können Sie die Ergebnisse auch erweitern, eingrenzen oder neu sortieren.
zur Hilfe zum gewählten Suchschlüssel, bitte klicken
Reinforcement Learning for Adaptive Dialogue Systems; Preface; Acknowledgements; Contents; Acronyms; Chapter 1 Introduction; 1.1 The Design Problem for Spoken Dialogue Systems; 1.2 Overview; 1.3 Structure of the Book; Chapter 2 (Background); Chapter 3 (Reinforcement Learning); Chapter 4 (Proof-of-Concept: Information Seeking Strategies); Chapter 5 (A Bootstrapping Approach to Develop Reinforcement Learning-based Strategies); Chapter 6 (Data Collection in aWizard-of-Oz Experiment); Chapter 7 (Building a Simulated Learning Environment from Wizard-of-Oz Data)
Chapter 8 (Comparing Reinforcement and Supervised Learning of Dialogue Policies with Real Users)Chapter 9 (Natural Language Generation); Chapter 10 (Conclusion); Part I Fundamental Concepts; Chapter 2 Background; 2.1 Human-Computer Interaction; 2.2 Dialogue Strategy Development; 2.2.1 Conventional Development Lifecycle; 2.2.2 Evaluation and Strategy Quality Control; 2.2.2.1 Quality Control in Industry; 2.2.2.2 Evaluation Practises in Academia; 2.2.2.3 The PARADISE Evaluation Framework; 2.2.2.4 Strategy Re-Implementation; 2.2.3 Strategy Implementation
2.2.3.1 Implementation Practises in Industry2.2.3.2 Implementation Practises in Academia; 2.2.4 Challenges for Strategy Development; 2.3 Literature review: Learning Dialogue Strategies; 2.3.1 Machine Learning Paradigms; 2.3.2 Supervised Learning for Dialogue Strategies; 2.3.3 Dialogue as Decision Making under Uncertainty; 2.3.4 Reinforcement Learning for Dialogue Strategies; 2.4 Summary; Chapter 3 Reinforcement Learning; 3.1 The Nature of Dialogue Interaction; 3.1.1 Dialogue is Temporal; 3.1.2 Dialogue is Dynamic; 3.2 Reinforcement Learning-based Dialogue Strategy Learning
3.2.1 Dialogue as a Markov Decision Process3.2.1.1 Representing Dialogue as a Markov Decision Process; 3.2.1.2 Partially Observable Markov Decision Processes for Strategy Learning; 3.2.2 The Reinforcement Learning Problem; 3.2.2.1 Elements of Reinforcement Learning; 3.2.2.2 Algorithms for Reinforcement Learning; 3.2.2.3 The Curse of Dimensionality, and State Space Reduction; 3.2.3 Model-based vs. Simulation-based Strategy Learning; 3.2.3.1 Model-based Reinforcement Learning; 3.2.3.2 Simulation-based Reinforcement Learning; 3.3 Dialogue Simulation; 3.3.1 Wizard-of-Oz Studies
3.3.2 Computer-based Simulations3.3.3 Discussion; 3.4 Application Domains; 3.4.1 Information-Seeking Dialogue Systems; 3.4.2 Multimodal Output Planning and Information Presentation; 3.4.3 Multimodal Dialogue Systems for In-Car Digital Music Players; 3.5 Summary; Chapter 4 Proof-of-Concept: Information Seeking Strategies; 4.1 Introduction; 4.1.1 A Proof-of-Concept Study; 4.2 Simulated Learning Environments; 4.2.1 Problem Representation; 4.2.2 Database Retrieval Simulations; 4.2.2.1 Monotonic Database Simulation; 4.2.2.2 Random Database Simulation; 4.2.3 Noise Model; 4.2.4 User Simulations
1.Introduction -- 2.Background -- 3.Reinforcement Learning for Information Seeking dialogue strategies -- 4.The bootstrapping approach to developing Reinforcement Learning-based strategies -- 5.Data Collection in aWizard-of-Oz experiment -- 6.Building a simulated learning environment from Wizard-of-Oz data -- 7.Comparing Reinforcement and Supervised Learning of dialogue policies with real users -- 8.Meta-evaluation -- 9.Adaptive Natural Language Generation -- 10.Conclusion -- References -- Example Dialogues -- A.1.Wizard-of-Oz Example Dialogues -- A.2.Example Dialogues from Simulated Interaction -- A.3.Example Dialogues from User Testing -- Learned State-Action Mappings -- Index
The past decade has seen a revolution in the field of spoken dialogue systems. As in other areas of Computer Science and Artificial Intelligence, data-driven methods are now being used to drive new methodologies for system development and evaluation. This book is a unique contribution to that ongoing change. A new methodology for developing spoken dialogue systems is described in detail. The journey starts and ends with human behaviour in interaction, and explores methods for learning from the data, for building simulation environments for training and testing systems, and for evaluating the results. The detailed material covers: Spoken and Multimodal dialogue systems, Wizard-of-Oz data collection, User Simulation methods, Reinforcement Learning, and Evaluation methodologies. The book is a research guide for students and researchers with a background in Computer Science, AI, or Machine Learning. It navigates through a detailed case study in data-driven methods for development and evaluation of spoken dialogue systems. Common challenges associated with this approach are discussed and example solutions are provided. This work provides insights, lessons, and inspiration for future research and development - not only for spoken dialogue systems in particular, but for data-driven approaches to human-machine interaction in general
Reinforcement Learning for Adaptive Dialogue Systems : A Data-driven Methodology for Dialogue Management and Natural Language Generation / Verena Rieser. Berlin, Heidelberg : Springer-Verlag Berlin Heidelberg, 2011
