JarKA: Modeling Attribute Interactions for Cross-lingual Knowledge Alignment

TL;DR

This paper introduces JarKA, a model that improves cross-lingual knowledge graph alignment by modeling attribute interactions and merging attribute-based and structural alignments, significantly outperforming existing methods.

Contribution

The paper proposes a novel framework that models attribute interactions for better entity and attribute alignment across KGs, addressing heterogeneity issues.

Findings

Outperforms state-of-the-art baselines by up to 38.48% HitRatio@1.

Can infer alignments between attributes, relationships, and values.

Effective in dealing with sparse and heterogeneous KG structures.

Abstract

Abstract. Cross-lingual knowledge alignment is the cornerstone in building a comprehensive knowledge graph (KG), which can benefit various knowledge-driven applications. As the structures of KGs are usually sparse, attributes of entities may play an important role in aligning the entities. However, the heterogeneity of the attributes across KGs prevents from accurately embedding and comparing entities. To deal with the issue, we propose to model the interactions between attributes, instead of globally embedding an entity with all the attributes. We further propose a joint framework to merge the alignments inferred from the attributes and the structures. Experimental results show that the proposed model outperforms the state-of-art baselines by up to 38.48% HitRatio@1. The results also demonstrate that our model can infer the alignments between attributes, relationships and values, in addition to entities.