Multi-view semantic enhancement model for few-shot knowledge graph completion

Abstract

In recent years, few-shot knowledge graph completion (FKGC) has gained popularity as a solution to the long-tail distribution problem of real-world knowledge graphs (KGs). The previous knowledge graph completion (KGC) models obtain triple representation merely relying on the structure view, ignoring the valuable semantic knowledge. In this paper, we propose a multi-view framework for few-shot relation learning to address the issue. Specifically, based the structural information of the graph obtained using the structure view, we add the text view and the commonsense view. The text view employs text descriptions of entities and relations to obtain a richer semantic representation. The commonsense view performs high-quality negative sampling based on complex relations. Moreover, commonsense semantic constraints are invoked to suppress the overfitting caused by the complexity of the relation matrix. Extensive experiments show that our model outperforms state-of-the-art FKGC methods on the frequently-used benchmark datasets FB15k237-One and NELL-One.