Data-Driven Methods for Adaptive Spoken Dialogue Systems: Computational Learning for Conversational InterfacesOliver Lemon, Olivier Pietquin Springer Science & Business Media, 21 Eki 2012 - 178 sayfa Data driven methods have long been used in Automatic Speech Recognition (ASR) and Text-To-Speech (TTS) synthesis and have more recently been introduced for dialogue management, spoken language understanding, and Natural Language Generation. Machine learning is now present “end-to-end” in Spoken Dialogue Systems (SDS). However, these techniques require data collection and annotation campaigns, which can be time-consuming and expensive, as well as dataset expansion by simulation. In this book, we provide an overview of the current state of the field and of recent advances, with a specific focus on adaptivity. |
İçindekiler
Chapter 1 Conversational Interfaces | 1 |
Chapter 2 Developing Dialogue Managers from Limited Amounts of Data | 5 |
Chapter 3 DataDriven Methods for Spoken Language Understanding | 19 |
Chapter 4 User Simulation in the Development of Statistical Spoken Dialogue Systems | 39 |
Chapter 5 Optimisation for POMDPBased Spoken Dialogue Systems | 74 |
Chapter 6 Statistical Approaches to Adaptive Natural Language Generation | 103 |
Chapter 7 Metrics and Evaluation of Spoken Dialogue Systems | 131 |
Chapter 8 DataDriven Methods in Industrial Spoken Dialog Systems | 151 |
Chapter 9 Conclusion and Future Research Directions | 172 |
Diğer baskılar - Tümünü görüntüle
Sık kullanılan terimler ve kelime öbekleri
action adapt algorithm annotated approach automated Bayesian network BN user call flow CLASSiC project classifiers Computational Linguistics corpus data sets Data-Driven Methods decision dialogue act dialogue management dialogue model dialogue policy dialogue quality dialogue strategies distribution domain estimate example Gaši´c Gaussian processes grammars handcrafted input interaction Keizer kernel Lemon M¨oller machine learning Mairesse Markov Markov decision processes metrics model parameters n-gram natural language nodes optimal output parser parsing performance Pieraccini Pietquin policy optimisation POMDP predict probability problem Proc Proceedings real users referring expressions reinforcement learning restaurant reward function Rieser SDSs Sect semantic tree Seventh Framework Programme SIGdial simulated user slot speech recognition spoken dialogue systems Spoken Language Springer Science+Business Media statistical stochastic supervised learning task completion Task Success TownInfo update user act user behaviour user goal user model User Satisfaction user simulation user’s utterances variables