Improved Knowledge Base Completion by the Path-Augmented TransR Model

被引：5

作者：

Huang, Wenhao ^{[1
,2
]}

Li, Ge ^{[1
,2
]}

Jin, Zhi ^{[1
,2
]}

机构：

[1] Peking Univ, Minist Educ, Key Lab High Confidence Software Technol, Beijing, Peoples R China

[2] Peking Univ, Software Inst, Beijing, Peoples R China

来源：

KNOWLEDGE SCIENCE, ENGINEERING AND MANAGEMENT (KSEM 2017): 10TH INTERNATIONAL CONFERENCE, KSEM 2017, MELBOURNE, VIC, AUSTRALIA, AUGUST 19-20, 2017, PROCEEDINGS | 2017年 / 10412卷

基金：

中国国家自然科学基金;

关键词：

Knowledge base completion; Relation path; Link prediction; ONTOLOGY;

D O I：

10.1007/978-3-319-63558-3_13

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

Knowledge base completion aims to infer new relations from existing information. In this paper, we propose path-augmented TransR (PTransR) model to improve the accuracy of link prediction. In our approach, we build PTransR based on TransR, which is the best one-hop model at present. Then we regularize TransR with information of relation paths. In our experiment, we evaluate PTransR on the task of entity prediction. Experimental results show that PTransR outperforms previous models.

引用

页码：149 / 159

页数：11

共 21 条

[1] [Anonymous], 1992, COLING 1992, DOI DOI 10.3115/992133.992154
[2] [Anonymous], 2013, P 2013 C N AM CHAPTE
[3] [Anonymous], 2013, ADV NEURAL INF PROCE
[4] [Anonymous], 2015, P 2015 C EMP METH NA, DOI 10.18653/v1/D15-1038
[5] [Anonymous], 2016, IJCAI
[6] [Anonymous], 2013, P 26 INT C NEUR INF
[7] [Anonymous], COLING
[8] [Anonymous], 2015, ARXIV150406580
[9] Gene Ontology: tool for the unification of biology
Ashburner, M
Ball, CA
Blake, JA
Botstein, D
Butler, H
Cherry, JM
Davis, AP
Dolinski, K
Dwight, SS
Eppig, JT
Harris, MA
Hill, DP
Issel-Tarver, L
Kasarskis, A
Lewis, S
Matese, JC
Richardson, JE
Ringwald, M
Rubin, GM
Sherlock, G
[J]. NATURE GENETICS, 2000, 25 (01) : 25 - 29
[10] Banko M, 2007, 20TH INTERNATIONAL JOINT CONFERENCE ON ARTIFICIAL INTELLIGENCE, P2670

← 1 2 3 →