An Application of Reinforcement Learning to Dialogue Strategy Selection in a Spoken Dialogue System for Email
نویسندگان
چکیده
منابع مشابه
An Application of Reinforcement Learning to Dialogue Strategy Selection in a Spoken Dialogue System for Email
This paper describes a novel method by which a spoken dialogue system can learn to choose an optimal dialogue strategy from its experience interacting with human users. The method is based on a combination of reinforcement learning and performance modeling of spoken dialogue systems. The reinforcement learning component applies Q-learning (Watkins, 1989), while the performance modeling componen...
متن کاملEvaluating Dialogue Strategies in a Spoken Dialogue System for Email
This paper presents an evaluation of directed dialogue (DD) and mixed initiative (MI) strategies in a spoken language system for Email. We compare the DD strategy, in which the system controls the dialog, to the MI strategy, in which users can flexibly control the dialog. For evaluating both strategies we used the PARADISE framework, which supports comparisons among dialogue strategies. Our exp...
متن کاملNJFun - A Reinforcement Learning Spoken Dialogue System
This paper describes NJFun, a real-time spoken dialogue systemthat-provides users with information about things to d~ in New Jersey. NJFun automatically optimizes its dialogue strategy over time, by using a methodology for applying reinforcement learning to a working dialogue system with human
متن کاملEvaluating Automatic Dialogue Strategy Adaptation for a Spoken Dialogue System
In this paper, we describe an empirical evaluation of an adaptive mixed initiative spoken dialogue system. We conducted two sets of experiments to evaluate the mixed initiative and automatic adaptation aspects of the system, and analyzed the resulting dialogues along three dimensions: performance factors, discourse features, and initiative distribution. Our results show that 1) both the mixed i...
متن کاملHierarchical Reinforcement Learning for Spoken Dialogue Systems
This thesis focuses on the problem of scalable optimization of dialogue behaviour in speech-based conversational systems using reinforcement learning. Most previous investigations in dialogue strategy learning have proposed flat reinforcement learning methods, which are more suitable for small-scale spoken dialogue systems. This research formulates the problem in terms of Semi-Markov Decision P...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Journal of Artificial Intelligence Research
سال: 2000
ISSN: 1076-9757
DOI: 10.1613/jair.713