NeuType: A Simple and Effective Neural Network Approach for Predicting Missing Entity Type Information in Knowledge Bases

TL;DR

NeuType introduces two neural network models that effectively predict missing entity types in knowledge bases using entity descriptions and related information, significantly improving over existing methods.

Contribution

The paper proposes simple neural network architectures for entity type prediction, leveraging entity descriptions and related data, with demonstrated superior performance on DBpedia.

Findings

Significant accuracy improvements over state-of-the-art methods.

Effective use of short entity descriptions and related entity information.

Validated on the DBpedia knowledge base.

Abstract

Knowledge bases store information about the semantic types of entities, which can be utilized in a range of information access tasks. This information, however, is often incomplete, due to new entities emerging on a daily basis. We address the task of automatically assigning types to entities in a knowledge base from a type taxonomy. Specifically, we present two neural network architectures, which take short entity descriptions and, optionally, information about related entities as input. Using the DBpedia knowledge base for experimental evaluation, we demonstrate that these simple architectures yield significant improvements over the current state of the art.