Cross-lingual Knowledge Graph Alignment via Graph Matching Neural Network

TL;DR

This paper introduces a graph matching neural network for cross-lingual knowledge graph alignment that leverages local sub-graphs of entities to improve matching accuracy across different KGs.

Contribution

It proposes the topic entity graph concept and a graph-attention based method to enhance entity matching by incorporating contextual information.

Findings

Outperforms previous state-of-the-art methods significantly

Effective use of local sub-graphs improves alignment accuracy

Graph-attention mechanism models local and global matching information

Abstract

Previous cross-lingual knowledge graph (KG) alignment studies rely on entity embeddings derived only from monolingual KG structural information, which may fail at matching entities that have different facts in two KGs. In this paper, we introduce the topic entity graph, a local sub-graph of an entity, to represent entities with their contextual information in KG. From this view, the KB-alignment task can be formulated as a graph matching problem; and we further propose a graph-attention based solution, which first matches all entities in two topic entity graphs, and then jointly model the local matching information to derive a graph-level matching vector. Experiments show that our model outperforms previous state-of-the-art methods by a large margin.