Extracting Short Entity Descriptions for Open-World Extension to Knowledge Graph Completion Models

Abstract

Great advances have been made in closed-world Knowledge Graph Completion (KGC). But it still remains a challenge for open-world KGC. A recently proposed open-world KGC model called OWE found a method to map the text space embedding obtained from the entity name and description to a pre-trained graph embedding space, by which OWE can extend the embedding-based KGC models to the open world. However, OWE uses average aggregation to obtain the text representation, no matter the entity description is long or short. It uses much unnecessary textual information and may become unstable. In this paper, we propose an extension to OWE, which is named OWE-MRC, to extract short expressions for entities from long descriptions by using a Machine Reading Comprehension (MRC) model. After obtaining short descriptions for entities, OWE-MRC uses the extension method of OWE to extend the embedding-based KGC models to the open world. We have applied OWE-MRC to extend common KGC models, such as ComplEx and Graph Neural Networks (GNNs) based models, to perform open-world link prediction. Our experiments on two datasets FB20k and DBPedia50k indicate that (1) the MRC model can effectively extract meaningful short descriptions; (2) our OWE-MRC uses much less textual information than OWE, but achieves competitive performance on open-world link prediction. In addition, we have used OWE to extend the GNN-based model to the open world. And our extended GNN model has achieved significant improvements on open-world link prediction comparing to the state-of-the-art open-world KGC models.