Knowledge Base Completion via Rule-Enhanced Relational Learning

被引：7

作者：

Guo, Shu ^{[1
,2
]}

Ding, Boyang ^{[1
,2
]}

Wang, Quan ^{[1
,2
]}

Wang, Lihong ^{[3
]}

Wang, Bin ^{[1
,2
]}

机构：

[1] Chinese Acad Sci, Inst Informat Engn, Beijing, Peoples R China

[2] Univ Chinese Acad Sci, Beijing, Peoples R China

[3] Coordinat Ctr China, Natl Comp Network Emergency Response Tech Team, Beijing, Peoples R China

来源：

KNOWLEDGE GRAPH AND SEMANTIC COMPUTING: SEMANTIC, KNOWLEDGE, AND LINKED BIG DATA | 2016年 / 650卷

基金：

中国国家自然科学基金;

关键词：

Knowledge base completion; Relational learning; Rules;

D O I：

10.1007/978-981-10-3168-7_22

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

Traditional relational learning techniques perform the knowledge base (KB) completion task based solely on observed facts, ignoring rich domain knowledge that could be extremely useful for inference. In this paper, we encode domain knowledge as simple rules, and propose rule-enhanced relational learning for KB completion. The key idea is to use rules to further refine the inference results given by traditional relational learning techniques, and hence improve the inference accuracy of them. Facts inferred in this way will be the most preferred by relational learning, and at the same time comply with all the rules. Experimental results show that by incorporating the domain knowledge, our approach achieve the best overall performance in the CCKS 2016 competition.

引用

页码：219 / 227

页数：9

共 48 条

[21] An Approach to Knowledge Base Completion by a Committee-Based Knowledge Graph Embedding [J].

Choi, Su Jeong ;

Song, Hyun-Je ;

Park, Seong-Bae .

APPLIED SCIENCES-BASEL, 2020, 10 (08)

[22] Pre-training and diagnosing knowledge base completion models [J].

Kocijan, Vid ;

Jang, Myeongjun ;

Lukasiewicz, Thomas .

ARTIFICIAL INTELLIGENCE, 2024, 329

[23] Knowledge Base Completion by Variational Bayesian Neural Tensor Decomposition [J].

He, Lirong ;

Liu, Bin ;

Li, Guangxi ;

Sheng, Yongpan ;

Wang, Yafang ;

Xu, Zenglin .

COGNITIVE COMPUTATION, 2018, 10 (06) :1075-1084

[24] A structure distinguishable graph attention network for knowledge base completion [J].

Xue Zhou ;

Bei Hui ;

Lizong Zhang ;

Kexi Ji .

Neural Computing and Applications, 2021, 33 :16005-16017

[25] FINE-GRAINED ENTITY TYPING FOR KNOWLEDGE BASE COMPLETION [J].

Jia, Yidong ;

Xu, Weiran ;

Qin, Pengda ;

Bao, Zuyi .

PROCEEDINGS OF 2016 5TH IEEE INTERNATIONAL CONFERENCE ON NETWORK INFRASTRUCTURE AND DIGITAL CONTENT (IEEE IC-NIDC 2016), 2016, :361-365

[26] Knowledge Base Completion by Variational Bayesian Neural Tensor Decomposition [J].

Lirong He ;

Bin Liu ;

Guangxi Li ;

Yongpan Sheng ;

Yafang Wang ;

Zenglin Xu .

Cognitive Computation, 2018, 10 :1075-1084

[27] CLUSTERING AND BOOTSTRAPPING BASED FRAMEWORK FOR NEWS KNOWLEDGE BASE COMPLETION [J].

Srinivasa, K. ;

Thilagam, P. Santhi .

COMPUTING AND INFORMATICS, 2021, 40 (02) :318-340

[28] A structure distinguishable graph attention network for knowledge base completion [J].

Zhou, Xue ;

Hui, Bei ;

Zhang, Lizong ;

Ji, Kexi .

NEURAL COMPUTING & APPLICATIONS, 2021, 33 (23) :16005-16017

[29] MultiE: Multi-Task Embedding for Knowledge Base Completion [J].

Zhang, Zhao ;

Zhuang, Fuzhen ;

Niu, Zheng-Yu ;

Wang, Deqing ;

He, Qing .

CIKM'18: PROCEEDINGS OF THE 27TH ACM INTERNATIONAL CONFERENCE ON INFORMATION AND KNOWLEDGE MANAGEMENT, 2018, :1715-1718

[30] Siamese Pre-Trained Transformer Encoder for Knowledge Base Completion [J].

Li, Mengyao ;

Wang, Bo ;

Jiang, Jing .

NEURAL PROCESSING LETTERS, 2021, 53 (06) :4143-4158

← 1 2 3 4 5 →