Enhancing Cross-Lingual Entity Alignment in Knowledge Graphs through Structure Similarity Rearrangement

Liu, Guiyang; Jin, Canghong; Shi, Longxiang; Yang, Cheng; Shuai, Jiangbing; Ying, Jing

doi:10.3390/s23167096

Open AccessArticle

Enhancing Cross-Lingual Entity Alignment in Knowledge Graphs through Structure Similarity Rearrangement

by

Guiyang Liu

^1,2,

Canghong Jin

^1,*

,

Longxiang Shi

¹,

Cheng Yang

¹,

Jiangbing Shuai

³ and

Jing Ying

²

¹

School of Computer and Computing Science, Hangzhou City University, Hangzhou 310015, China

²

College of Computer Science and Technology, Zhejiang University, Hangzhou 310027, China

³

Zhejiang Academy of Science & Technology for Inspection & Quarantine, Hangzhou 310051, China

^*

Author to whom correspondence should be addressed.

Sensors 2023, 23(16), 7096; https://doi.org/10.3390/s23167096

Submission received: 26 June 2023 / Revised: 22 July 2023 / Accepted: 7 August 2023 / Published: 10 August 2023

(This article belongs to the Special Issue Advanced Semantic Technologies and Sensors)

Download

Browse Figures

Review Reports Versions Notes

Abstract

Cross-lingual entity alignment in knowledge graphs is a crucial task in knowledge fusion. This task involves learning low-dimensional embeddings for nodes in different knowledge graphs and identifying equivalent entities across them by measuring the distances between their representation vectors. Existing alignment models use neural network modules and the nearest neighbors algorithm to find suitable entity pairs. However, these models often ignore the importance of local structural features of entities during the alignment stage, which may lead to reduced matching accuracy. Specifically, nodes that are poorly represented may not benefit from their surrounding context. In this article, we propose a novel alignment model called SSR, which leverages the node embedding algorithm in graphs to select candidate entities and then rearranges them by local structural similarity in the source and target knowledge graphs. Our approach improves the performance of existing approaches and is compatible with them. We demonstrate the effectiveness of our approach on the DBP15k dataset, showing that it outperforms existing methods while requiring less time.

Keywords: knowledge graph; cross-lingual entity alignment; structural similarity rearrangement

Share and Cite

MDPI and ACS Style

Liu, G.; Jin, C.; Shi, L.; Yang, C.; Shuai, J.; Ying, J. Enhancing Cross-Lingual Entity Alignment in Knowledge Graphs through Structure Similarity Rearrangement. Sensors 2023, 23, 7096. https://doi.org/10.3390/s23167096

AMA Style

Liu G, Jin C, Shi L, Yang C, Shuai J, Ying J. Enhancing Cross-Lingual Entity Alignment in Knowledge Graphs through Structure Similarity Rearrangement. Sensors. 2023; 23(16):7096. https://doi.org/10.3390/s23167096

Chicago/Turabian Style

Liu, Guiyang, Canghong Jin, Longxiang Shi, Cheng Yang, Jiangbing Shuai, and Jing Ying. 2023. "Enhancing Cross-Lingual Entity Alignment in Knowledge Graphs through Structure Similarity Rearrangement" Sensors 23, no. 16: 7096. https://doi.org/10.3390/s23167096

APA Style

Liu, G., Jin, C., Shi, L., Yang, C., Shuai, J., & Ying, J. (2023). Enhancing Cross-Lingual Entity Alignment in Knowledge Graphs through Structure Similarity Rearrangement. Sensors, 23(16), 7096. https://doi.org/10.3390/s23167096

Note that from the first issue of 2016, this journal uses article numbers instead of page numbers. See further details here.

Article Menu

Enhancing Cross-Lingual Entity Alignment in Knowledge Graphs through Structure Similarity Rearrangement

Abstract

Share and Cite

Article Metrics

Article Access Statistics

Further Information

Guidelines

MDPI Initiatives

Follow MDPI