Relation-Aware Neighborhood Aggregation for Cross-lingual Entity Alignment

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

1 Scopus citations

Abstract

Cross-lingual entity alignment refers to linking entities in different language knowledge graphs if they are of identical meaning. Recent works focus on learning structure information of knowledge graphs and calculate the distance of entity embeddings for entity alignment. However, the GCN-based methods may bring noise from neighbors due to the heterogeneity of knowledge graphs. Besides, relations, as inherent attribute of knowledge graph, should be merged into the structure learning. In this paper, a relation-aware neighborhood aggregation model RANA is proposed to solve cross-lingual entity alignment task. The specific relation semantics are modeled to modify the aggregation weights of neighbors. CSLS and knowledge graph completion are introduced to enhance the alignment metric and structural information respectively. Experiments on real-world datasets demonstrate that RANA significantly outperforms other baselines in alignment accuracy and robustness.

Original languageEnglish
Title of host publicationProceedings of 2021 IEEE 24th International Conference on Information Fusion, FUSION 2021
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781737749714
StatePublished - 2021
Event24th IEEE International Conference on Information Fusion, FUSION 2021 - Sun City, South Africa
Duration: 1 Nov 20214 Nov 2021

Publication series

NameProceedings of 2021 IEEE 24th International Conference on Information Fusion, FUSION 2021

Conference

Conference24th IEEE International Conference on Information Fusion, FUSION 2021
Country/TerritorySouth Africa
CitySun City
Period1/11/214/11/21

Keywords

  • Entity alignment
  • Knowledge graph embedding
  • Relation-aware graph attention network

Fingerprint

Dive into the research topics of 'Relation-Aware Neighborhood Aggregation for Cross-lingual Entity Alignment'. Together they form a unique fingerprint.

Cite this