This book helps develop a better understanding of how researchers from different scientific backgrounds view models and uncertainty. It provides key steps in fostering and encouraging interdisciplinary research, which is vital in addressing several big issues that society faces today, such as climate change, longevity, financial and actuarial risk management. To make progress in these areas, researchers must develop an understanding of differing perspectives and methods of those working in other disciplines.This title presents the views and understandings of eminent people in their respective fields through interviews on the topic of modelling and uncertainty. Each expert was asked the same set of questions to help readers understand the similarities and differences existing between various disciplines. It also helps to bridge some of the gaps encountered by those carrying out inter- and multi-disciplinary research and suggests new approaches to modelling and uncertainty quantification.

Focuses on the aim to develop software tools to assist users in constructing and evaluating arguments and counterarguments and/or to develop automated systems for constructing and evaluating arguments and counterarguments. This book includes articles, which provide a snapshot of research questions in the area of computational models of argument.

This volume includes proceedings articles presented at the Workshop on Paralinguistic Information and its Integration in Spoken Dialogue Systems held in Granada, Spain. The material focuses on the three broad areas of spoken dialogue systems for robotics, emotions and spoken dialogue systems, and Spoken dialogue systems for real-world applications The workshop proceedings are part of the 3rd Annual International Workshop on Spoken Dialogue Systems, which brings together researchers from all over the world working in the field of spoken dialogue systems. It provides an international forum for the presentation of research and applications, and for lively discussions among researchers as well as industrialists.

This book discusses the Partially Observable Markov Decision Process (POMDP) framework applied in dialogue systems. It presents POMDP as a formal framework to represent uncertainty explicitly while supporting automated policy solving. The authors propose and implement an end-to-end learning approach for dialogue POMDP model components. Starting from scratch, they present the state, the transition model, the observation model and then finally the reward model from unannotated and noisy dialogues. These altogether form a significant set of contributions that can potentially inspire substantial further work. This concise manuscript is written in a simple language, full of illustrative examples, figures, and tables.

One of the goals of artificial intelligence (AI) is creating autonomous agents that must make decisions based on uncertain and incomplete information. The goal is to design rational agents that must take the best action given the information available and their goals. Decision Theory Models for Applications in Artificial Intelligence: Concepts and Solutions provides an introduction to different types of decision theory techniques, including MDPs, POMDPs, Influence Diagrams, and Reinforcement Learning, and illustrates their application in artificial intelligence. This book provides insights into the advantages and challenges of using decision theory models for developing intelligent systems.

A comprehensive overview of the state-of-the-art in natural language generation for interactive systems, with links to resources for further research.

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.