XJIPC OpenIR  > 多语种信息技术研究室
Structural Optimization and Online Evolutionary Learning for Spoken Dialog Management
Ren, H (Ren, Hang); Yan, YH (Yan, Yonghong)
2016
发表期刊IEEE SIGNAL PROCESSING LETTERS
卷号23期号:7页码:1013-1017
摘要Designing dialog management (DM) policies that are robust to environmental noises is a nontrivial task. Approaches based on reinforcement learning (RL) are popular in academia and have been empirically shown to exhibit much better performance than handcrafted policies. However, the policies trained using RL are mostly incomprehensible, thus limiting the deployments for commercial applications. Policy optimization using genetic algorithm (GA) is a relatively new approach to spoken DM. The most notable advantage of this approach is that the trained policies can be directly interpreted by human experts. In this letter, we make several contributions to the GA-based framework. First, a structural policy learning procedure is presented. Second, a new fitness estimation method based on fitted policy evaluation is proposed. Finally, combining with these methods, an online evolutionary policy learning algorithm is designed which is much more data efficient than direct policy search using Monte Carlo simulations. These proposed approaches are empirically evaluated and compared with several state-of-the-art methods in a simulated environment. The experiments show favorable results for our approach.
关键词Human-computer Interaction Speech Processing Genetic Algorithms
DOI10.1109/LSP.2016.2574890
收录类别SCI
WOS记录号WOS:000379694800009
引用统计
被引频次:1[WOS]   [WOS记录]     [WOS相关记录]
文献类型期刊论文
条目标识符http://ir.xjipc.cas.cn/handle/365002/4652
专题多语种信息技术研究室
作者单位1.Chinese Acad Sci, Inst Acoust, Key Lab Speech Acoust & Content Understanding, Beijing 100190, Peoples R China
2.Chinese Acad Sci, Xinjiang Tech Inst Phys & Chem, Xinjiang Lab Minor Speech & Language Informat Pro, Beijing, Peoples R China
推荐引用方式
GB/T 7714
Ren, H ,Yan, YH . Structural Optimization and Online Evolutionary Learning for Spoken Dialog Management[J]. IEEE SIGNAL PROCESSING LETTERS,2016,23(7):1013-1017.
APA Ren, H ,&Yan, YH .(2016).Structural Optimization and Online Evolutionary Learning for Spoken Dialog Management.IEEE SIGNAL PROCESSING LETTERS,23(7),1013-1017.
MLA Ren, H ,et al."Structural Optimization and Online Evolutionary Learning for Spoken Dialog Management".IEEE SIGNAL PROCESSING LETTERS 23.7(2016):1013-1017.
条目包含的文件
文件名称/大小 文献类型 版本类型 开放类型 使用许可
Structural Optimizat(290KB)期刊论文作者接受稿开放获取CC BY-NC-SA浏览 请求全文
个性服务
推荐该条目
保存到收藏夹
查看访问统计
导出为Endnote文件
谷歌学术
谷歌学术中相似的文章
[Ren, H (Ren, Hang)]的文章
[Yan, YH (Yan, Yonghong)]的文章
百度学术
百度学术中相似的文章
[Ren, H (Ren, Hang)]的文章
[Yan, YH (Yan, Yonghong)]的文章
必应学术
必应学术中相似的文章
[Ren, H (Ren, Hang)]的文章
[Yan, YH (Yan, Yonghong)]的文章
相关权益政策
暂无数据
收藏/分享
文件名: Structural Optimization and Online Evolutionary Learning for Spoken Dialog Management.pdf
格式: Adobe PDF
此文件暂不支持浏览
所有评论 (0)
暂无评论
 

除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。