APSIPA Transactions on Signal and Information Processing > Vol 12 > Issue 1

TypeEA: Type-Associated Embedding for Knowledge Graph Entity Alignment

Xiou Ge, University of Southern California, USA, xiouge@usc.edu , Yun Cheng Wang, University of Southern California, USA, Bin Wang, National University of Singapore, Singapore, C.-C. Jay Kuo, University of Southern California, USA
 
Suggested Citation
Xiou Ge, Yun Cheng Wang, Bin Wang and C.-C. Jay Kuo (2023), "TypeEA: Type-Associated Embedding for Knowledge Graph Entity Alignment", APSIPA Transactions on Signal and Information Processing: Vol. 12: No. 1, e5. http://dx.doi.org/10.1561/116.00000139

Publication Date: 21 Feb 2023
© 2023 X. Ge, Y. C. Wang, B. Wang and C.-C. Jay Kuo
 
Subjects
 
Keywords
Knowledge graphentity alignmenttype embeddings
 

Share

Open Access

This is published under the terms of CC BY-NC.

Downloaded: 1058 times

In this article:
Introduction 
Related Work 
The TypeEA Method 
Experiments 
Conclusion and Future Work 
References 

Abstract

Entity alignment is commonly used to link different knowledge graphs and augment facts about entities. The main objective is to identify the counterpart of a source entity in the target knowledge graph. Although the auxiliary information such as textual, visual, and temporal features was leveraged to improve the entity alignment performance in the past, the entity type information is rarely considered in existing entity alignment models. In this paper, we demonstrate that the entity type information, which is commonly available in knowledge graphs, is very helpful to knowledge graph alignment and propose a new method called the Type-associated Entity Alignment (TypeEA) accordingly. TypeEA exploits the entity type information to guide entity alignment models so that they can focus on entities with matching types. A type embedding model based on semantic matching is developed in TypeEA to capture the association between types in different knowledge graphs. Experimental results show that the proposed TypeEA consistently outperforms state-of-the-art baselines across all OpenEA entity alignment datasets with different experimental settings.

DOI:10.1561/116.00000139