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
[1]  
[Anonymous], 2015, ACL
[2]  
[Anonymous], 2017, Representation learning on graphs: methods and applications
[3]  
[Anonymous], 2010, P 23 INT C COMP LING, DOI 10.3115/1119176.1119181
[4]   DBpedia: A nucleus for a web of open data [J].
Auer, Soeren ;
Bizer, Christian ;
Kobilarov, Georgi ;
Lehmann, Jens ;
Cyganiak, Richard ;
Ives, Zachary .
SEMANTIC WEB, PROCEEDINGS, 2007, 4825 :722-+
[5]  
Bollacker K, 2008, P 2008 ACM SIGMOD IN, P1247, DOI DOI 10.1145/1376616.1376746
[6]  
Bordes A., 2011, AAAI C ARTIF INTELL, P301
[7]  
Bordes A., 2013, ADV NEURAL INFORM PR, P2787
[8]  
Bordes Antoine, 2014, MACHINE LEARNING, V2014
[9]  
Buneman Peter, 2016, PROC VLDB ENDOW
[10]  
Campbell W. M., 2016, ARXIV160801386V1