Knowledge Graph Completion with Text-aided Regularization

TL;DR

This paper enhances knowledge graph completion by integrating text-based information into the regularization process of embedding models, leading to improved prediction accuracy.

Contribution

It introduces a novel text-aided regularization method that leverages related textual data to improve knowledge graph embedding performance.

Findings

Improved accuracy over baseline KG embedding methods

Effective use of textual similarity in regularization

Demonstrated benefits across multiple datasets

Abstract

Knowledge Graph Completion is a task of expanding the knowledge graph/base through estimating possible entities, or proper nouns, that can be connected using a set of predefined relations, or verb/predicates describing interconnections of two things. Generally, we describe this problem as adding new edges to a current network of vertices and edges. Traditional approaches mainly focus on using the existing graphical information that is intrinsic of the graph and train the corresponding embeddings to describe the information; however, we think that the corpus that are related to the entities should also contain information that can positively influence the embeddings to better make predictions. In our project, we try numerous ways of using extracted or raw textual information to help existing KG embedding frameworks reach better prediction results, in the means of adding a similarity function to the regularization part in the loss function. Results have shown that we have made decent improvements over baseline KG embedding methods.