Bayesian methods for machine learning have been widely investigated, yielding principled
methods for incorporating prior information into inference algorithms. In this survey, we …

During the past decade, several areas of speech and language understanding have
witnessed substantial breakthroughs from the use of data-driven models. In the area of …

Autonomous systems are increasingly used in highly variable and uncertain environments
giving rise to the pressing need to consider risk in both the synthesis and verification of …

This thesis presents a new modelling framework for dialogue management based on the
concept of probabilistic rules. Probabilistic rules are defined as if... then... else constructions …

Reinforcement learning is now an acknowledged approach for optimizing the interaction
strategy of spoken dialogue systems. If the first considered algorithms were quite basic (like …

The main goal in task planning is to build a sequence of actions that takes an agent from an
initial state to a goal state. In robotics, this is particularly difficult because actions usually …

Reinforcement techniques have been successfully used to maximise the expected
cumulative reward of statistical dialogue systems. Typically, reinforcement learning is used …

Natural language is a flexible and powerful control modality which can transform a
wheelchair from a vehicle into a genuine helper. While autonomous wheelchairs are …

Reinforcement learning methods are increasingly used to optimise dialogue policies from
experience. Most current techniques are model-free: they directly estimate the utility of …

We propose a software architecture designed to ease the implementation of dialogue
systems. The Modular Architecture for Conversational Agents (MACA) uses a plug-n-play …