Dual-factor Generation Model for Conversation

doi:10.1145/3394052

	Dual-factor Generation Model for Conversation
	Zhang, Ruqing 1,2; Guo, Jiafeng 1,2; Fan, Yixing 1,2; Lan, Yanyan 1,2; Cheng, Xueqi 1,2
	2020-06-01
发表期刊	ACM TRANSACTIONS ON INFORMATION SYSTEMS
ISSN	1046-8188
卷号	38 期号:3 页码:31
摘要	The conversation task is usually formulated as a conditional generation problem, i.e., to generate a natural and meaningful response given the input utterance. Generally speaking, this formulation is apparently based on an oversimplified assumption that the response is solely dependent on the input utterance. It ignores the subjective factor of the responder, e.g., his/her emotion or knowledge state, which is a major factor that affects the response in practice. Without explicitly differentiating such subjective factor behind the response, existing generation models can only learn the general shape of conversations, leading to the blandness problem of the response. Moreover, there is no intervention mechanism within the existing generation process, since the response is fully decided by the input utterance. In this work, we propose to view the conversation task as a dual-factor generation problem, including an objective factor denoting the input utterance and a subjective factor denoting the responder state. We extend the existing neural sequence-to-sequence (Seq2Seq) model to accommodate the responder state modeling. We introduce two types of responder state, i.e., discrete and continuous state, to model emotion state and topic preference state, respectively. We show that with our dual-factor generation model, we can not only better fit the conversation data, but also actively control the generation of the response with respect to sentiment or topic specificity.
关键词	Conversation dual-factor generation responder state modeling
DOI	10.1145/3394052
收录类别	SCI
语种	英语
资助项目	Beijing Academy of Artificial Intelligence (BAAI)[BAAI2019ZD0306] ; National Natural Science Foundation of China (NSFC)[61722211] ; National Natural Science Foundation of China (NSFC)[61773362] ; National Natural Science Foundation of China (NSFC)[61872338] ; National Natural Science Foundation of China (NSFC)[61902381] ; Youth Innovation Promotion Association CAS[20144310] ; Youth Innovation Promotion Association CAS[2016102] ; National Key RD Program of China[2016QY02D0405] ; Lenovo-CAS Joint Lab Youth Scientist Project ; Foundation and Frontier Research Key Program of Chongqing Science and Technology Commission[cstc2017jcyjBX0059]
WOS研究方向	Computer Science
WOS类目	Computer Science, Information Systems
WOS记录号	WOS:000583695800011
出版者	ASSOC COMPUTING MACHINERY
引用统计	被引频次：2[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/2XEOYT63/16093
专题	中国科学院计算技术研究所期刊论文_英文
通讯作者	Guo, Jiafeng
作者单位	1.Univ Chinese Acad Sci, Beijing, Peoples R China 2.Chinese Acad Sci, Inst Comp Technol, CAS Key Lab Network Data Sci & Technol, 6 Kexueyuan South Rd, Beijing 100190, Peoples R China
推荐引用方式 GB/T 7714	Zhang, Ruqing,Guo, Jiafeng,Fan, Yixing,et al. Dual-factor Generation Model for Conversation[J]. ACM TRANSACTIONS ON INFORMATION SYSTEMS,2020,38(3):31.
APA	Zhang, Ruqing,Guo, Jiafeng,Fan, Yixing,Lan, Yanyan,&Cheng, Xueqi.(2020).Dual-factor Generation Model for Conversation.ACM TRANSACTIONS ON INFORMATION SYSTEMS,38(3),31.
MLA	Zhang, Ruqing,et al."Dual-factor Generation Model for Conversation".ACM TRANSACTIONS ON INFORMATION SYSTEMS 38.3(2020):31.