Knowledge triple mining via multi-task learning

doi:10.1016/j.is.2018.09.003

CORC > 计算技术研究所 > 中国科学院计算技术研究所 > 中国科学院计算技术研究所期刊论文 > 英文

	Knowledge triple mining via multi-task learning
	He, Qing 3,4; He, Jia 3,4; Zhang, Zhao 3,4; Niu, Zheng-Yu 2; Li, Xuebing 4; Zhuang, Fuzhen 3,4; Xiong, Hui 1
刊名	INFORMATION SYSTEMS
	2019-02-01
卷号	80 页码:64-75
关键词	Multi-task learning Knowledge mining Relation extraction Knowledge graph construction
ISSN号	0306-4379
DOI	10.1016/j.is.2018.09.003
英文摘要	Recent years have witnessed the rapid development of knowledge bases (KBs) such as WordNet, Yago and DBpedia, which are useful resources in Al-related applications. However, most of the existing KBs are suffering from incompleteness and manually adding knowledge into KBs is inefficient. Therefore, automatically mining knowledge becomes a critical issue. To this end, in this paper, we propose to develop a model (S-2 AMT) to extract knowledge triples, such as , from the Internet and add them to KBs to support many downstream applications. Particularly, because the seed instances' for every relation is difficult to obtain, our model is capable of mining knowledge triples with limited available seed instances. To be more specific, we treat the knowledge triple mining task for each relation as a single task and use multi-task learning (MTL) algorithms to solve the problem, because MTL algorithms can often get better results than single-task learning (STL) ones with limited training data. Moreover, since finding proper task groups is a fatal problem in MTL which can directly influences the final results, we adopt a clustering algorithm to find proper task groups to further improve the performance. Finally, we conduct extensive experiments on real-world data sets and the experimental results clearly validate the performance of our MTL algorithms against STL ones. (C) 2018 Elsevier Ltd. All rights reserved.
资助项目	National Key Research and Development Program of China[2018YFB1004300] ; National Natural Science Foundation of China[61773361] ; National Natural Science Foundation of China[61473273] ; National Natural Science Foundation of China[91546122] ; Guangdong provincial science and technology plan projects[2015 B010109005] ; Project of Youth Innovation Promotion Association CAS[2017146]
WOS研究方向	Computer Science
语种	英语
出版者	PERGAMON-ELSEVIER SCIENCE LTD
WOS记录号	WOS:000454964800005
内容类型	期刊论文
源URL	[http://119.78.100.204/handle/2XEOYT63/3492]
专题	中国科学院计算技术研究所期刊论文_英文
通讯作者	Zhuang, Fuzhen
作者单位	1.Rutgers State Univ, Rutgers Business Sch, Management Sci & Informat Syst Dept, Newark, NJ USA 2.Baidu Inc, Beijing, Peoples R China 3.Univ Chinese Acad Sci, Beijing 100049, Peoples R China 4.Chinese Acad Sci, Inst Comp Technol, Key Lab Intelligent Informat Proc, Beijing 100190, Peoples R China
推荐引用方式 GB/T 7714	He, Qing,He, Jia,Zhang, Zhao,et al. Knowledge triple mining via multi-task learning[J]. INFORMATION SYSTEMS,2019,80:64-75.
APA	He, Qing.,He, Jia.,Zhang, Zhao.,Niu, Zheng-Yu.,Li, Xuebing.,...&Xiong, Hui.(2019).Knowledge triple mining via multi-task learning.INFORMATION SYSTEMS,80,64-75.
MLA	He, Qing,et al."Knowledge triple mining via multi-task learning".INFORMATION SYSTEMS 80(2019):64-75.