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
Source PublicationIEEE SIGNAL PROCESSING LETTERS
ISSN1070-9908
Volume23Issue:7Pages:1013-1017
Abstract

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.

KeywordHuman-computer Interaction Speech Processing Genetic Algorithms
DOI10.1109/LSP.2016.2574890
Indexed BySCI
WOS IDWOS:000379694800009
Citation statistics
Cited Times:1[WOS]   [WOS Record]     [Related Records in WOS]
Document Type期刊论文
Identifierhttp://ir.xjipc.cas.cn/handle/365002/4652
Collection多语种信息技术研究室
Affiliation1.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
Recommended Citation
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.
Files in This Item:
File Name/Size DocType Version Access License
Structural Optimizat(290KB)期刊论文作者接受稿开放获取CC BY-NC-SAView Application Full Text
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Ren, H (Ren, Hang)]'s Articles
[Yan, YH (Yan, Yonghong)]'s Articles
Baidu academic
Similar articles in Baidu academic
[Ren, H (Ren, Hang)]'s Articles
[Yan, YH (Yan, Yonghong)]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Ren, H (Ren, Hang)]'s Articles
[Yan, YH (Yan, Yonghong)]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: Structural Optimization and Online Evolutionary Learning for Spoken Dialog Management.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.