Combining embedding-based and symbol-based methods for entity alignment

被引:15
作者
Jiang, Tingting [1 ,2 ,3 ]
Bu, Chenyang [1 ,2 ,3 ]
Zhu, Yi [1 ,2 ,4 ]
Wu, Xindong [1 ,3 ,5 ]
机构
[1] Hefei Univ Technol, Minist Educ, Key Lab Knowledge Engn Big Data, Hefei, Peoples R China
[2] Hefei Univ Technol, Sch Comp Sci & Informat Engn, Hefei, Peoples R China
[3] Hefei Univ Technol, Inst Big Knowledge Sci, Hefei, Peoples R China
[4] Yangzhou Univ, Sch Informat Engn, Yangzhou, Jiangsu, Peoples R China
[5] Mininglamp Technol, Mininglamp Acad Sci, Beijing, Peoples R China
基金
中国国家自然科学基金;
关键词
Entity alignment; Knowledge graph embedding; String Similarity;
D O I
10.1016/j.patcog.2021.108433
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
The objective of entity alignment is to judge whether entities refer to the same object in the real world. Methods for entity alignment can be grossly divided into two groups: conventional symbol-based entity alignment methods and embedding-based entity alignment methods. Both groups of methods have advantages and disadvantages (which are detailed in Section 1). Therefore, combining the advantages of both methods might be a promising strategy. However, to the best of our knowledge, only the RTEA algorithm that was proposed in our previous conference paper (Proceeding of Pacific Rim International Conference on Artificial Intelligence, pp. 162-175, 2019) utilizes this strategy for entity alignment. This manuscript is an extended version of that conference paper, in which an improved algorithm, namely, ESEA (combining embedding-based and symbol-based methods for entity alignment), is proposed based on the following steps. First, a novel method for combining embedding models with symbol-based models is proposed. Entities with high vector similarities are obtained through a hybrid embedding model, and the final aligned entity pairs are calculated via symbol-based methods. Second, a series of symbol based methods, instead of only the edit distance method in the original version, are combined with embedding-based methods for relation alignment. Third, we combine symbol-based and embedding based methods in a more complicated framework with the objective of better exploiting the advantages of both methods. The experimental results on real-world datasets demonstrate that the proposed method outperformed several state-of-the-art embedding-based entity alignment approaches and outperformed our previous RTEA method.(c) 2021 Elsevier Ltd. All rights reserved.
引用
收藏
页数:14
相关论文
共 43 条
[1]   Deep depth-based representations of graphs through deep learning networks [J].
Bai, Lu ;
Cui, Lixin ;
Bai, Xiao ;
Hancock, Edwin R. .
NEUROCOMPUTING, 2019, 336 :3-12
[2]  
Bordes A., 2013, P 26 INT C NEUR INF, V2, P2787
[3]   A semantic matching energy function for learning with multi-relational data Application to word-sense disambiguation [J].
Bordes, Antoine ;
Glorot, Xavier ;
Weston, Jason ;
Bengio, Yoshua .
MACHINE LEARNING, 2014, 94 (02) :233-259
[4]  
Cao YX, 2019, 57TH ANNUAL MEETING OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS (ACL 2019), P1452
[5]  
Chen M., 2016, P IJCAI, P1511
[6]  
Chen MH, 2018, PROCEEDINGS OF THE TWENTY-SEVENTH INTERNATIONAL JOINT CONFERENCE ON ARTIFICIAL INTELLIGENCE, P3998
[7]  
Guo S., 2016, P 2016 C EMPIRICAL M, P192
[8]   A Joint Embedding Method for Entity Alignment of Knowledge Bases [J].
Hao, Yanchao ;
Zhang, Yuanzhe ;
He, Shizhu ;
Liu, Kang ;
Zhao, Jun .
KNOWLEDGE GRAPH AND SEMANTIC COMPUTING: SEMANTIC, KNOWLEDGE, AND LINKED BIG DATA, 2016, 650 :3-14
[9]  
Hu Wei, 2019, CEUR WORKSHOP P, P189
[10]   Statistical pattern recognition: A review [J].
Jain, AK ;
Duin, RPW ;
Mao, JC .
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2000, 22 (01) :4-37