Knowledge Augmented Dialogue Generation with Divergent Facts Selection

doi:10.1016/j.knosys.2020.106479

	Knowledge Augmented Dialogue Generation with Divergent Facts Selection
	Jiang, Bin 4; Yang, Jingxu 4; Yang, Chao 4; Zhou, Wanyue 4; Pang, Liang 1; Zhou, Xiaokang 2,3
刊名	KNOWLEDGE-BASED SYSTEMS
	2020-12-27
卷号	210 页码:11
关键词	Open-domain dialogue systems Knowledge selection Subject drift Attention mechanism
ISSN号	0950-7051
DOI	10.1016/j.knosys.2020.106479
英文摘要	The end-to-end open-domain dialogue system is a challenging task since the existing neural models suffer from the issue of trivial responses. Employing background knowledge as a major solution, has been proven to be effective to improve the responses quality. However, less attention was paid to the selection of the appropriate knowledge in scenarios where the utterance subject drifts between two partners, which could prohibit the model from learning to access knowledge correctly. In this paper, we propose a novel Knowledge Augmented Dialogue Generation (KADG) model to facilitate both knowledge selection and incorporation in open-domain dialogue systems. The core components of KADG consist of Divergent Knowledge Selector (DKS) and Knowledge Aware Decoder (KAD). DKS performs a one-hop subject reasoning over knowledge by pre-optimizing each knowledge candidate with inferred drift clue. Drift clue implies the potential subjects association of the current conversation and is served to bridge the subject gap in the knowledge selection. Thereafter, KAD makes full use of this selected knowledge to generate responses contextual coherently as well as knowledgeably. Comprehensive experiments on a newly released knowledge-grounded conversation dataset Wizard-of-Wikipedia have verified the superiority of our model than previous baselines and shown that our method can refer to the knowledge properly and generate diverse and informative responses. (C) 2020 Elsevier B.V. All rights reserved.
资助项目	National Natural Science Foundation of China[61702176] ; National Natural Science Foundation of China[61906180] ; CAS Key Lab of Network Data Science and Technology, Institute of Computing Technology, Chinese Academy of Sciences
WOS研究方向	Computer Science
语种	英语
出版者	ELSEVIER
WOS记录号	WOS:000600972100012
内容类型	期刊论文
源URL	[http://119.78.100.204/handle/2XEOYT63/16579]
专题	中国科学院计算技术研究所
通讯作者	Jiang, Bin
作者单位	1.Chinese Acad Sci, Inst Comp Technol, CAS Key Lab Network Data Sci & Technol, Beijing 100190, Peoples R China 2.RIKEN, RIKEN Ctr Adv Intelligence Project, Tokyo 1030027, Japan 3.Shiga Univ, Fac Data Sci, Hikone 5228522, Japan 4.Hunan Univ, Coll Comp Sci & Elect Engn, Changsha 410082, Peoples R China
推荐引用方式 GB/T 7714	Jiang, Bin,Yang, Jingxu,Yang, Chao,et al. Knowledge Augmented Dialogue Generation with Divergent Facts Selection[J]. KNOWLEDGE-BASED SYSTEMS,2020,210:11.
APA	Jiang, Bin,Yang, Jingxu,Yang, Chao,Zhou, Wanyue,Pang, Liang,&Zhou, Xiaokang.(2020).Knowledge Augmented Dialogue Generation with Divergent Facts Selection.KNOWLEDGE-BASED SYSTEMS,210,11.
MLA	Jiang, Bin,et al."Knowledge Augmented Dialogue Generation with Divergent Facts Selection".KNOWLEDGE-BASED SYSTEMS 210(2020):11.