.png){kind=icon}
返回
Gaussian Processes for POMDP-Based Dialogue Manager Optimization
.png){kind=icon}
OA
AI
DOI：10.1109/TASL.2013.2282190.png)
.png){kind=icon}
.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
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.
Keyword:
Gaussian process
POMDP
statistical dialog systems
AI总结
对已上传原文的论文进行重点信息的提取，主要内容包括：简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。
期刊
I
IF:
5.1
论文数:
2.6K
被引数:
1.1W
机构
引用论文
Establishment of Analytical Method for Chlorophyll Using the N,N-Dimethylformamide and Dimethylsulfoxide in Citrus Leaves利用N,N-二甲基甲酰胺和二甲基亚砜建立柑橘叶片中叶绿素的分析方法
OAAI
.png){kind=icon}
OAAI分享收藏分享收藏The Hidden Information State model: A practical framework for POMDP-based spoken dialogue managementOAAI
OAAI分享收藏分享收藏
查看更多内容