• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文期刊>Computer speech and language >Evaluation of a hierarchical reinforcement learning spoken dialogue system
【24h】

Evaluation of a hierarchical reinforcement learning spoken dialogue system

机译：评估分层强化学习口语对话系统

获取原文
获取原文并翻译 | 示例
           
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

We describe an evaluation of spoken dialogue strategies designed using hierarchical reinforcement learning agents. The dialogue strategies were learnt in a simulated environment and tested in a laboratory setting with 32 users. These dialogues were used to evaluate three types of machine dialogue behaviour: hand-coded, fully-learnt and semi-learnt. These experiments also served to evaluate the realism of simulated dialogues using two proposed metrics contrasted with 'Precision-Recall'. The learnt dialogue behaviours used the Semi-Markov Decision Process (SMDP) model, and we report the first evaluation of this model in a realistic conversational environment. Experimental results in the travel planning domain provide evidence to support the following claims: (a) hierarchical semi-learnt dialogue agents are a better alternative (with higher overall performance) than deterministic or fully-learnt behaviour; (b) spoken dialogue strategies learnt with highly coherent user behaviour and conservative recognition error rates (keyword error rate of 20%) can outperform a reasonable hand-coded strategy; and (c) hierarchical reinforcement learning dialogue agents are feasible and promising for the (semi) automatic design of optimized dialogue behaviours in larger-scale systems.
机译：我们描述了使用分层强化学习代理设计的口语对话策略的评估。对话策略是在模拟环境中学习的，并在32位用户的实验室环境中进行了测试。这些对话用于评估三种类型的机器对话行为：手工编码，完全学习和半学习。这些实验还可以用来评估模拟对话的真实性，它使用了两个与“精确召回”相比拟议的指标。学习到的对话行为使用了半马尔可夫决策过程（SMDP）模型，我们在现实的对话环境中报告了对该模型的首次评估。在旅行计划领域的实验结果提供了支持以下主张的证据：（a）与确定性或完全学习的行为相比，等级半学习型对话代理是更好的选择（具有更高的总体性能）； （b）以高度连贯的用户行为和保守的识别错误率（关键字错误率为20％）来学习的口语对话策略，可以胜过合理的手工编码策略； （c）分层强化学习对话代理对于大规模系统中优化对话行为的（半）自动设计是可行的并且很有前途。

著录项

  • 来源
    《Computer speech and language》 |2010年第2期|395-429|共35页
  • 作者

    Heriberto Cuayahuitl; Steve Renals; Oliver Lemon; Hiroshi Shimodaira;

  • 作者单位

    Institute for Communicating and Collaborative Systems, School of Informatics, University of Edinburgh, 10 Crichlon Street, Edinburgh EH8 9AB, Scotland, UK;

    Institute for Communicating and Collaborative Systems, School of Informatics, University of Edinburgh, 10 Crichlon Street, Edinburgh EH8 9AB, Scotland, UK;

    Institute for Communicating and Collaborative Systems, School of Informatics, University of Edinburgh, 10 Crichlon Street, Edinburgh EH8 9AB, Scotland, UK;

    Institute for Communicating and Collaborative Systems, School of Informatics, University of Edinburgh, 10 Crichlon Street, Edinburgh EH8 9AB, Scotland, UK;

  • 收录信息 美国《科学引文索引》(SCI);美国《工程索引》(EI);
  • 原文格式 PDF
  • 正文语种 eng
  • 中图分类
  • 关键词

    spoken dialogue systems; hierarchical reinforcement learning; human-machine dialogue simulation; dialogue strategies; system evaluation;

    机译：口语对话系统;分层强化学习;人机对话模拟;对话策略;系统评估;

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱：kefu@zhangqiaokeyan.com

京公网安备：11010802029741号 ICP备案号：京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有

  • 客服微信

  • 服务号