Automatic Optimization of Dialogue Management
ثبت نشده
چکیده
Designing the dialogue strategy of a spoken dialogue system involves many nontrivial choices. This paper presents a reinforcement learning approach for automatically optimizing dialogue strategy. We first present a practical methodology that addresses the technical challenges in applying reinforcement learning to a working dialogue system with human users. We then demonstrate how we have used this methodology to measurably improve performance in a large-scale experimental system.
منابع مشابه
Learning what to say and how to say it: Joint optimisation of spoken dialogue management and natural language generation
This paper argues that the problems of dialogue management (DM) and Natural Language Generation (NLG) in dialogue systems are closely related and can be fruitfully treated statistically, in a joint optimisation framework such as that provided by Reinforcement Learning (RL). We first review recent results and methods in automatic learning of dialogue management strategies for spoken and multimod...
متن کاملSpoken Dialogue Management Using Hierarchical Reinforcement Learning and Dialogue Simulation
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...
متن کاملComparing ASR modeling methods for spoken dialogue simulation and optimal strategy learning
Speech enabled interfaces are nowadays becoming ubiquitous. The most advanced ones rely on probabilistic pattern matching systems and especially on automatic speech recognition systems. Because of their statistical nature, performances of such systems never reach one hundred percent of correct recognition results. Performances are linked to environmental noise and to intraand inter-speaker vari...
متن کاملUsing Markov decision process for learning dialogue strategies
In this paper we introduce a stochastic model for dialogue systems based on Markov decision process. Within this framework we show that the problem of dialogue strategy design can be stated as an optimization problem, and solved by a variety of methods, including the reinforcement learning approach. The advantages of this new paradigm include objective evaluation of dialogue systems and their a...
متن کاملHierarchical Reinforcement Learning of Dialogue Policies in a development environment for dialogue systems: REALL-DUDE
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...
متن کامل