LinkNBed: Multi-Graph Representation Learning with Entity Linkage

被引:26
作者
Trivedi, Rakshit [1 ]
Sisman, Bunyamin [2 ]
Ma, Jun [2 ]
Faloutsos, Christos [2 ,3 ]
Zha, Hongyuan [1 ]
Dong, Xin Luna [2 ]
机构
[1] Georgia Tech, Coll Comp, Atlanta, GA 30332 USA
[2] Amazon Com, Seattle, WA USA
[3] CMU, SCS, Pittsburgh, PA USA
来源
PROCEEDINGS OF THE 56TH ANNUAL MEETING OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS (ACL), VOL 1 | 2018年
关键词
D O I
10.18653/v1/P18-1024
中图分类号
TP39 [计算机的应用];
学科分类号
081203 ; 0835 ;
摘要
Knowledge graphs have emerged as an important model for studying complex multi-relational data. This has given rise to the construction of numerous large scale but incomplete knowledge graphs encoding information extracted from various resources. An effective and scalable approach to jointly learn over multiple graphs and eventually construct a unified graph is a crucial next step for the success of knowledge-based inference for many downstream applications. To this end, we propose LinkNBed, a deep relational learning framework that learns entity and relationship representations across multiple graphs. We identify entity linkage across graphs as a vital component to achieve our goal. We design a novel objective that leverage entity linkage and build an efficient multi-task training procedure. Experiments on link prediction and entity linkage demonstrate substantial improvements over the state-of-the-art relational learning approaches.
引用
收藏
页码:252 / 262
页数:11
相关论文
共 42 条
[11]  
Carlson A., 2010, AAAI, V5, P3
[12]   Personalized Recommendations using Knowledge Graphs: A Probabilistic Logic Programming Approach [J].
Catherine, Rose ;
Cohen, William .
PROCEEDINGS OF THE 10TH ACM CONFERENCE ON RECOMMENDER SYSTEMS (RECSYS'16), 2016, :325-332
[13]  
Cui Wanyun, 2017, PROC VLDB ENDOW
[14]   Entity Query Feature Expansion using Knowledge Base Links [J].
Dalton, Jeffrey ;
Dietz, Laura ;
Allan, James .
SIGIR'14: PROCEEDINGS OF THE 37TH INTERNATIONAL ACM SIGIR CONFERENCE ON RESEARCH AND DEVELOPMENT IN INFORMATION RETRIEVAL, 2014, :365-374
[15]  
Deng, 2015, P INT C LEARN REPR I
[16]   Knowledge Vault: A Web-Scale Approach to Probabilistic Knowledge Fusion [J].
Dong, Xin Luna ;
Gabrilovich, Evgeniy ;
Heitz, Geremy ;
Horn, Wilko ;
Lao, Ni ;
Murphy, Kevin ;
Strohmann, Thomas ;
Sun, Shaohua ;
Zhang, Wei .
PROCEEDINGS OF THE 20TH ACM SIGKDD INTERNATIONAL CONFERENCE ON KNOWLEDGE DISCOVERY AND DATA MINING (KDD'14), 2014, :601-610
[17]  
Fang Wei., 2016, CoNLL
[18]  
Feng Jun, 2016, COLING 2016 26 INT C, P641
[19]  
Gabrilovich Evgeniy, 2009, J ARTIF INT RES
[20]  
Globerson A, 2016, PROCEEDINGS OF THE 54TH ANNUAL MEETING OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS, VOL 1, P621