JarKA: Modeling Attribute Interactions for Cross-lingual Knowledge Alignment
This work addresses the challenge of aligning heterogeneous attributes across knowledge graphs for improved cross-lingual applications, representing an incremental advancement in the field.
The paper tackles the problem of cross-lingual knowledge alignment in sparse knowledge graphs by modeling attribute interactions rather than globally embedding entities, resulting in a model that outperforms state-of-the-art baselines by up to 38.48% in HitRatio@1.
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.