End-to-End Personalized Humorous Response Generation in Untrimmed Multi-Role Dialogue System

doi:10.1109/ACCESS.2019.2926830

	End-to-End Personalized Humorous Response Generation in Untrimmed Multi-Role Dialogue System
	Yang, Qichuan 1; He, Zhiqiang 1,2,3; Zhan, Zhiqiang 2; Li, Rang 3; Lee, Yanwei 3; Zhang, Yang 3; Hu, Changjian 3
	2019
发表期刊	IEEE ACCESS
ISSN	2169-3536
卷号	7 页码:94059-94071
摘要	Multi-role dialogue is challenging in natural language processing (NLP), which needs not only to understand sentences but also to simulate interaction among roles. However, the existing methods assume that only two speakers are present in a conversation. In real life, this assumption is not always valid. More often, there are multiple speakers involved. To address this issue, we propose a multi-role interposition dialogue system (MIDS) that generates reasonable responses based on the dialogue context and next speaker prediction. The MIDS employs multiply role-defined encoders to understand each speaker and an independent sequence model to predict the next speaker. The independent sequence model also works as a controller to integrate encoders with weights. Then, an attention-enhanced decoder generates responses based on the dialogue context, speaker prediction, and integrated encoders. Moreover, with the help of unique speaker prediction, the MIDS is able to generate diverse responses and allow itself to join (interpose) the conversation when appropriate. Furthermore, a novel reward function and an updating policy of reinforcement learning (RL) are applied to the MIDS, which further enable MIDS the ability to write drama scripts. The experimental results demonstrate that the MIDS offers a significant improvement to the accuracy of speaker prediction and the reduction of response generation perplexity. It is also able to interact with users without cues during real-life online conversations and avoid meaningless conversation loops while generating scripts. This paper marks the first step toward multi-role humorous dialogue generation.
关键词	Dialogue generation multi-role conversation neural network reinforcement learning speaker prediction
DOI	10.1109/ACCESS.2019.2926830
收录类别	SCI
语种	英语
WOS研究方向	Computer Science ; Engineering ; Telecommunications
WOS类目	Computer Science, Information Systems ; Engineering, Electrical & Electronic ; Telecommunications
WOS记录号	WOS:000477867900029
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
引用统计	被引频次：3[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://119.78.100.204/handle/2XEOYT63/4515
专题	中国科学院计算技术研究所期刊论文_英文
通讯作者	Zhang, Yang
作者单位	1.Beihang Univ, Sch Comp Sci & Engn, Beijing 100083, Peoples R China 2.Chinese Acad Sci, Inst Comp Technol, Beijing 100190, Peoples R China 3.Lenovo Ltd, Res & Dev, Beijing 100094, Peoples R China
推荐引用方式 GB/T 7714	Yang, Qichuan,He, Zhiqiang,Zhan, Zhiqiang,et al. End-to-End Personalized Humorous Response Generation in Untrimmed Multi-Role Dialogue System[J]. IEEE ACCESS,2019,7:94059-94071.
APA	Yang, Qichuan.,He, Zhiqiang.,Zhan, Zhiqiang.,Li, Rang.,Lee, Yanwei.,...&Hu, Changjian.(2019).End-to-End Personalized Humorous Response Generation in Untrimmed Multi-Role Dialogue System.IEEE ACCESS,7,94059-94071.
MLA	Yang, Qichuan,et al."End-to-End Personalized Humorous Response Generation in Untrimmed Multi-Role Dialogue System".IEEE ACCESS 7(2019):94059-94071.