期刊
COMPUTER SPEECH AND LANGUAGE
卷 28, 期 4, 页码 873-887出版社
ACADEMIC PRESS LTD- ELSEVIER SCIENCE LTD
DOI: 10.1016/j.csl.2013.12.002
关键词
Spoken dialogue systems; Dialogue management; Belief compression
资金
- Engineering and Physical Sciences Research Council, UK (EPSRC) [EP/G069840/1]
- European Commission's Framework 7 Programme (SPACEBOOK project) [270019]
- Engineering and Physical Sciences Research Council [EP/G069840/1] Funding Source: researchfish
- EPSRC [EP/G069840/1] Funding Source: UKRI
This article describes an evaluation of a POMDP-based spoken dialogue system (SDS), using crowdsourced calls with real users. The evaluation compares a Hidden Information State POMDP system which uses a hand-crafted compression of the belief space, with the same system instead using an automatically computed belief space compression. Automatically computed compressions are a way of introducing automation into the design process of statistical SDSs and promise a principled way of reducing the size of the very large belief spaces which often make POMDP approaches intractable. This is the first empirical comparison of manual and automatic approaches on a problem of realistic scale (restaurant, pub and coffee shop domain) with real users. The evaluation took 2193 calls from 85 users. After filtering for minimal user participation the two systems were compared on more than 1000 calls. (C) 2013 Elsevier Ltd. All rights reserved.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据