Incorporating Literals into Knowledge Graph Embeddings

TL;DR

This paper introduces LiteralE, a flexible extension for knowledge graph embeddings that incorporates literal information like properties, significantly enhancing link prediction performance across various datasets.

Contribution

LiteralE provides a simple, learnable method to integrate literal data into existing embedding models, improving their effectiveness in link prediction tasks.

Findings

LiteralE improves link prediction accuracy.

Incorporating literals enhances embedding models.

The approach is effective across multiple datasets.

Abstract

Knowledge graphs, on top of entities and their relationships, contain other important elements: literals. Literals encode interesting properties (e.g. the height) of entities that are not captured by links between entities alone. Most of the existing work on embedding (or latent feature) based knowledge graph analysis focuses mainly on the relations between entities. In this work, we study the effect of incorporating literal information into existing link prediction methods. Our approach, which we name LiteralE, is an extension that can be plugged into existing latent feature methods. LiteralE merges entity embeddings with their literal information using a learnable, parametrized function, such as a simple linear or nonlinear transformation, or a multilayer neural network. We extend several popular embedding models based on LiteralE and evaluate their performance on the task of link prediction. Despite its simplicity, LiteralE proves to be an effective way to incorporate literal information into existing embedding based methods, improving their performance on different standard datasets, which we augmented with their literals and provide as testbed for further research.