CSpace  > 中国科学院计算技术研究所期刊论文  > 英文
Knowledge Augmented Dialogue Generation with Divergent Facts Selection
Jiang, Bin1; Yang, Jingxu1; Yang, Chao1; Zhou, Wanyue1; Pang, Liang2; Zhou, Xiaokang3,4
2020-12-27
发表期刊KNOWLEDGE-BASED SYSTEMS
ISSN0950-7051
卷号210页码:11
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.
关键词Open-domain dialogue systems Knowledge selection Subject drift Attention mechanism
DOI10.1016/j.knosys.2020.106479
收录类别SCI
语种英语
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
WOS类目Computer Science, Artificial Intelligence
WOS记录号WOS:000600972100012
出版者ELSEVIER
引用统计
被引频次:9[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/2XEOYT63/16580
专题中国科学院计算技术研究所期刊论文_英文
通讯作者Jiang, Bin
作者单位1.Hunan Univ, Coll Comp Sci & Elect Engn, Changsha 410082, Peoples R China
2.Chinese Acad Sci, Inst Comp Technol, CAS Key Lab Network Data Sci & Technol, Beijing 100190, Peoples R China
3.Shiga Univ, Fac Data Sci, Hikone 5228522, Japan
4.RIKEN, RIKEN Ctr Adv Intelligence Project, Tokyo 1030027, Japan
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.
条目包含的文件
条目无相关文件。
个性服务
推荐该条目
保存到收藏夹
查看访问统计
导出为Endnote文件
谷歌学术
谷歌学术中相似的文章
[Jiang, Bin]的文章
[Yang, Jingxu]的文章
[Yang, Chao]的文章
百度学术
百度学术中相似的文章
[Jiang, Bin]的文章
[Yang, Jingxu]的文章
[Yang, Chao]的文章
必应学术
必应学术中相似的文章
[Jiang, Bin]的文章
[Yang, Jingxu]的文章
[Yang, Chao]的文章
相关权益政策
暂无数据
收藏/分享
所有评论 (0)
暂无评论
 

除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。