Data structures and software tools for the computer aided design of control systems: a survey.

CAD software can be structured as a set of modular 'software tools' only if there is some agreement on the data structures which are to be passed between tools. Beyond this basic requirement, it is desirable to give the agreed structures the status of 'data types' in the language used for interactive design. The ultimate refinement is to have a data management capability which 'understands' how to manipulate such data types. In this paper the requirements of CACSD are formulated from the point of view of Database Management Systems. Progress towards meeting these requirements in both the DBMS and the CACSD community is reviewed. The conclusion reached is that there has been considerable movement towards the realisation of software tools for CACSD, but that this owes more to modern ideas about programming languages, than to DBMS developments. The DBMS field has identified some useful concepts, but further significant progress is expected to come from the exploitation of concepts such as object-oriented programming, logic programming, or functional programming.

Reinforcement learning for parameter estimation in statistical spoken dialogue systems

Reinforcement techniques have been successfully used to maximise the expected cumulative reward of statistical dialogue systems. Typically, reinforcement learning is used to estimate the parameters of a dialogue policy which selects the system's responses based on the inferred dialogue state. However, the inference of the dialogue state itself depends on a dialogue model which describes the expected behaviour of a user when interacting with the system. Ideally the parameters of this dialogue model should be also optimised to maximise the expected cumulative reward. This article presents two novel reinforcement algorithms for learning the parameters of a dialogue model. First, the Natural Belief Critic algorithm is designed to optimise the model parameters while the policy is kept fixed. This algorithm is suitable, for example, in systems using a handcrafted policy, perhaps prescribed by other design considerations. Second, the Natural Actor and Belief Critic algorithm jointly optimises both the model and the policy parameters. The algorithms are evaluated on a statistical dialogue system modelled as a Partially Observable Markov Decision Process in a tourist information domain. The evaluation is performed with a user simulator and with real users. The experiments indicate that model parameters estimated to maximise the expected reward function provide improved performance compared to the baseline handcrafted parameters. © 2011 Elsevier Ltd. All rights reserved.

Real user evaluation of spoken dialogue systems using Amazon Mechanical Turk

This paper describes a framework for evaluation of spoken dialogue systems. Typically, evaluation of dialogue systems is performed in a controlled test environment with carefully selected and instructed users. However, this approach is very demanding. An alternative is to recruit a large group of users who evaluate the dialogue systems in a remote setting under virtually no supervision. Crowdsourcing technology, for example Amazon Mechanical Turk (AMT), provides an efficient way of recruiting subjects. This paper describes an evaluation framework for spoken dialogue systems using AMT users and compares the obtained results with a recent trial in which the systems were tested by locally recruited users. The results suggest that the use of crowdsourcing technology is feasible and it can provide reliable results. Copyright © 2011 ISCA.