We report on the design, construction and empirical evaluation of a large-scale spoken dialogue system that optimizes its performance via reinforcement learning on human user dialogue data.

Speech-based human-computer interaction faces several difficult challenges in order to be more widely accepted. One of the challenges in spoken dialogue management is to control the dialogue flow (dialogue strategy) in an efficient and natural way. Dialogue strategies designed by humans are prone to errors, labour-intensive and non-portable, making automatic design an attractive alternative. Pr...

Major steps towards dialogue models is to know about the basic units that are used to construct a dialogue model and possible sequences. In this approach a set of dialogue acts is not predefined by any theory or manually described during the engineering process, but is learned integrating different kind of data that are available in an avised spoken dialogue system. For this purpose an existing...

Over several years, we have developed an approach to spoken dialogue systems that includes rule-based and trainable dialogue managers, spoken language understanding and generation modules, and a comprehensive dialogue system architecture. We present a Reinforcement Learning-based dialogue system that goes beyond standard rule-based models and computes on-line decisions of the best dialogue move...

We examine correlations between dialogue characteristics and learning in two corpora of spoken tutoring dialogues: a human-human corpus and a humancomputer corpus, both of which have been manually annotated with dialogue acts relative to the tutoring domain. The results from our human-computer corpus show that the presence of student utterances that display reasoning, as well as the presence of...

Application of reinforcement learning methods in the development of dialogue strategies that support robust and efficient human–computer interaction using spoken language is a growing research area. In spoken dialogue system, Markov Decision Processes (MDPs) provide a formal framework for making dialogue management decisions for planning. This framework enables the system to learn the value of ...

We demonstrate the REALL-DUDE system1, which is a combination of REALL, an environment for Hierarchical Reinforcement Learning, and DUDE, a development environment for “Information State Update” dialogue systems (Lemon and Liu, 2006) which allows non-expert developers to produce complete spoken dialogue systems based only on a Business Process Model (BPM) and SQL database describing their appli...

A common problem in spoken dialogue systems is finding the intention of the user. This problem deals with obtaining one or several topics for each transcribed, possibly noisy, sentence of the user. In this work, we apply the recent unsupervised learning method, Hidden Topic Markov Models (HTMM), for finding the intention of the user in dialogues. This technique combines two methods of Latent Di...

We present DEAL, a spoken dialogue system for conversation training under development at KTH. DEAL is a game with a spoken language interface designed for second language learners. The system is intended as a multidisciplinary research platform where challenges and potential benefits of combining elements from computer games, dialogue systems and language learning can be explored.

Next-generation autonomous agents will be expected to converse with people to achieve their mutual goals. Human-machine dialogue, however, is challenged by noisy acoustic data, and by people’s preference for more natural interaction. This paper describes an ambitious project that embeds human subjects in a spoken dialogue system. It collects a rich and novel data set, including spoken dialogue,...