Gaussian processes for fast policy optimisation of POMDP-based dialogue managers

Modelling dialogue as a Partially Observable Markov Decision Process (POMDP) enables a dialogue policy robust to speech understanding errors to be learnt. However, a major challenge in POMDP policy learning is to maintain tractability, so the use of approximation is inevitable. We propose applying Gaussian Processes in Reinforcement learning of optimal POMDP dialogue policies, in order (1) to make the learning process faster and (2) to obtain an estimate of the uncertainty of the approximation. We first demonstrate the idea on a simple voice mail dialogue task and then apply this method to a real-world tourist information dialogue task. © 2010 Association for Computational Linguistics.

On-line policy optimisation of spoken dialogue systems via live interaction with human subjects

Statistical dialogue models have required a large number of dialogues to optimise the dialogue policy, relying on the use of a simulated user. This results in a mismatch between training and live conditions, and significant development costs for the simulator thereby mitigating many of the claimed benefits of such models. Recent work on Gaussian process reinforcement learning, has shown that learning can be substantially accelerated. This paper reports on an experiment to learn a policy for a real-world task directly from human interaction using rewards provided by users. It shows that a usable policy can be learnt in just a few hundred dialogues without needing a user simulator and, using a learning strategy that reduces the risk of taking bad actions. The paper also investigates adaptation behaviour when the system continues learning for several thousand dialogues and highlights the need for robustness to noisy rewards. © 2011 IEEE.

Partially Observable Markov Decision Processes with continuous observations for dialogue management

This work shows how a dialogue model can be represented as a Partially Observable Markov Decision Process (POMDP) with observations composed of a discrete and continuous component. The continuous component enables the model to directly incorporate a confidence score for automated planning. Using a testbed simulated dialogue management problem, we show how recent optimization techniques are able to find a policy for this continuous POMDP which outperforms a traditional MDP approach. Further, we present a method for automatically improving handcrafted dialogue managers by incorporating POMDP belief state monitoring, including confidence score information. Experiments on the testbed system show significant improvements for several example handcrafted dialogue managers across a range of operating conditions.

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.

Uncertainty management for on-line optimisation of a POMDP-based large-scale spoken dialogue system

The optimization of dialogue policies using reinforcement learning (RL) is now an accepted part of the state of the art in spoken dialogue systems (SDS). Yet, it is still the case that the commonly used training algorithms for SDS require a large number of dialogues and hence most systems still rely on artificial data generated by a user simulator. Optimization is therefore performed off-line before releasing the system to real users. Gaussian Processes (GP) for RL have recently been applied to dialogue systems. One advantage of GP is that they compute an explicit measure of uncertainty in the value function estimates computed during learning. In this paper, a class of novel learning strategies is described which use uncertainty to control exploration on-line. Comparisons between several exploration schemes show that significant improvements to learning speed can be obtained and that rapid and safe online optimisation is possible, even on a complex task. Copyright © 2011 ISCA.

N-best error simulation for training spoken dialogue systems

A recent trend in spoken dialogue research is the use of reinforcement learning to train dialogue systems in a simulated environment. Past researchers have shown that the types of errors that are simulated can have a significant effect on simulated dialogue performance. Since modern systems typically receive an N-best list of possible user utterances, it is important to be able to simulate a full N-best list of hypotheses. This paper presents a new method for simulating such errors based on logistic regression, as well as a new method for simulating the structure of N-best lists of semantics and their probabilities, based on the Dirichlet distribution. Off-line evaluations show that the new Dirichlet model results in a much closer match to the receiver operating characteristics (ROC) of the live data. Experiments also show that the logistic model gives confusions that are closer to the type of confusions observed in live situations. The hope is that these new error models will be able to improve the resulting performance of trained dialogue systems. © 2012 IEEE.

Policy optimisation of POMDP-based dialogue systems without state space compression

The partially observable Markov decision process (POMDP) has been proposed as a dialogue model that enables automatic improvement of the dialogue policy and robustness to speech understanding errors. It requires, however, a large number of dialogues to train the dialogue policy. Gaussian processes (GP) have recently been applied to POMDP dialogue management optimisation showing an ability to substantially increase the speed of learning. Here, we investigate this further using the Bayesian Update of Dialogue State dialogue manager. We show that it is possible to apply Gaussian processes directly to the belief state, removing the need for a parametric policy representation. In addition, the resulting policy learns significantly faster while maintaining operational performance. © 2012 IEEE.

Continuous asr for flexible incremental dialogue

Spoken dialogue systems provide a convenient way for users to interact with a machine using only speech. However, they often rely on a rigid turn taking regime in which a voice activity detection (VAD) module is used to determine when the user is speaking and decide when is an appropriate time for the system to respond. This paper investigates replacing the VAD and discrete utterance recogniser of a conventional turn-taking system with a continuously operating recogniser that is always listening, and using the recogniser 1-best path to guide turn taking. In this way, a flexible framework for incremental dialogue management is possible. Experimental results show that it is possible to remove the VAD component and successfully use the recogniser best path to identify user speech, with more robustness to noise, potentially smaller latency times, and a reduction in overall recognition error rate compared to using the conventional approach. © 2013 IEEE.

On-line policy optimisation of Bayesian spoken dialogue systems via human interaction

A partially observable Markov decision process has been proposed as a dialogue model that enables robustness to speech recognition errors and automatic policy optimisation using reinforcement learning (RL). However, conventional RL algorithms require a very large number of dialogues, necessitating a user simulator. Recently, Gaussian processes have been shown to substantially speed up the optimisation, making it possible to learn directly from interaction with human users. However, early studies have been limited to very low dimensional spaces and the learning has exhibited convergence problems. Here we investigate learning from human interaction using the Bayesian Update of Dialogue State system. This dynamic Bayesian network based system has an optimisation space covering more than one hundred features, allowing a wide range of behaviours to be learned. Using an improved policy model and a more robust reward function, we show that stable learning can be achieved that significantly outperforms a simulator trained policy. © 2013 IEEE.

Gaussian processes for POMDP-based dialogue manager optimization

A partially observable Markov decision process (POMDP) has been proposed as a dialog model that enables automatic optimization of the dialog policy and provides robustness to speech understanding errors. Various approximations allow such a model to be used for building real-world dialog systems. However, they require a large number of dialogs to train the dialog policy and hence they typically rely on the availability of a user simulator. They also require significant designer effort to hand-craft the policy representation. We investigate the use of Gaussian processes (GPs) in policy modeling to overcome these problems. We show that GP policy optimization can be implemented for a real world POMDP dialog manager, and in particular: 1) we examine different formulations of a GP policy to minimize variability in the learning process; 2) we find that the use of GP increases the learning rate by an order of magnitude thereby allowing learning by direct interaction with human users; and 3) we demonstrate that designer effort can be substantially reduced by basing the policy directly on the full belief space thereby avoiding ad hoc feature space modeling. Overall, the GP approach represents an important step forward towards fully automatic dialog policy optimization in real world systems. © 2013 IEEE.

Dialogue for bass clarinet and bassoon

This work specifically focuses on the lower register of both instruments, an area I've been led to explore as a result of my profound high frequency hearing loss. It was selected for performance following an international competitive call for scores and premiered at the 16th London New Wind Festival, 22nd November 2013. It was performed by Phil Edwards (bass clarinet) and Glyn Williams (bassoon).

What children learn from adults’ utterances: an ephemeral lexical boost and persistent syntactic priming in adult–child dialogue

We show that children’s syntactic production is immediately affected by individual experiences of structures and verb–structure pairings within a dialogue, but that these effects have different timecourses. In a picture-matching game, three- to four-year-olds were more likely to describe a transitive action using a passive immediately after hearing the experimenter produce a passive than an active (abstract priming), and this tendency was stronger when the verb was repeated (lexical boost). The lexical boost disappeared after two intervening utterances, but the abstract priming effect persisted. This pattern did not differ significantly from control adults. Children also showed a cumulative priming effect. Our results suggest that whereas the same mechanism may underlie children’s immediate syntactic priming and long-term syntactic learning, different mechanisms underlie the lexical boost versus long-term learning of verb–structure links. They also suggest broad continuity of syntactic processing in production between this age group and adults.

Aspects of Semantics and Pragmatics of Dialogue. SemDial 2010, 14th Workshop on the Semantics and Pragmatics of Dialogue

The papers collected in this book cover a range of topics in semantics and pragmatics of dialogue. All these papers were presented at SemDial 2010, the 14th Workshop on the Semantics and Pragmatics of Dialogue. This 14th edition in the SemDial series, also known as PozDial, took place in Poznań (Poland) in June 2010, and was organized by the Chair of Logic and Cognitive Science (Institute of Psychology, Adam Mickiewicz University). From over 30 submissions overall, 14 were accepted as full papers for plenary presentation at the workshop, and all are included in this book. In addition, 10 were accepted as posters, and are included here as 2-4 page short papers. Finally, we also include abstracts from our keynote speakers. We hope that the ideas gathered in this book will be a valuable source of up-to-date achievements in the field, and will become a valuable inspiration for new ones. We would like to express our thanks to all those who submitted to and participated in SemDial 2010, especially the invited speakers: Dale Barr (University of Glasgow), Jonathan Ginzburg (King's College London), Jeroen Groenendijk (University of Amsterdam) and Henry Prakken (Utrecht University, The University of Groningen). Last but not least, we would like to thank everybody engaged in the workshop organization -- the chairs, the local organizing committee for their hard work in Poznań, and the programme committee members for their thorough and helpful reviews.