Autonomous Sub-domain Modeling for Dialogue Policy with Hierarchical Deep Reinforcement Learning

CORC > 沈阳自动化研究所 > 中国科学院沈阳自动化研究所 > 空间自动化技术研究室

	Autonomous Sub-domain Modeling for Dialogue Policy with Hierarchical Deep Reinforcement Learning
	Kristianto, Giovanni Yoko 3; Zhang HW(张会文)1,2; Tong, Bin 3; Iwayama, Makoto 3; Kobayashi, Yoshiyuki 3
	2018
会议日期	October 31, 2018
会议地点	Brussels, Belgium
页码	9-16
英文摘要	Solving composites tasks, which consist of several inherent sub-tasks, remains a challenge in the research area of dialogue. Current studies have tackled this issue by manually decomposing the composite tasks into several sub-domains. However, much human effort is inevitable. This paper proposes a dialogue framework that autonomously models meaningful sub-domains and learns the policy over them. Our experiments show that our framework outperforms the baseline without sub-domains by 11% in terms of success rate, and is competitive with that with manually defined sub-domains.
产权排序	2
会议录	2nd International Workshop on Search-Oriented Conversational AI, SCAI 2018
会议录出版者	Association for Computational Linguistics
会议录出版地	Stroudsburg PA, USA
语种	英语
ISBN号	978-1-948087-75-9
内容类型	会议论文
源URL	[http://ir.sia.cn/handle/173321/30279]
专题	沈阳自动化研究所_空间自动化技术研究室
通讯作者	Kristianto, Giovanni Yoko
作者单位	1.Shenyang Institute of Automation, Chinese Academy of Sciences, Shenyang, China 2.University of Chinese Academy of Sciences, Beijing, China 3.Hitachi Central Research Laboratory, Tokyo, Japan
推荐引用方式 GB/T 7714	Kristianto, Giovanni Yoko,Zhang HW,Tong, Bin,et al. Autonomous Sub-domain Modeling for Dialogue Policy with Hierarchical Deep Reinforcement Learning[C]. 见:. Brussels, Belgium. October 31, 2018.