Do Judge an Entity by its Name! Entity Typing using Language Models

Russa Biswas, Radina Sofronova, Mehwish Alam, Nicolas Heist, Heiko Paulheim, Harald Sack

Keywords: Entity Type Prediction · Knowledge Graph Completion · Deep Neural Networks.

TL;DR: Entity typing in KGs only from the labels exploiting the language models

Abstract: The entity type information in a Knowledge Graph (KG) plays an important role in a wide range of applications in Natural Language Processing such as entity linking, question answering, relation extraction, etc. However, entity types are often noisy and incomplete. Entity Typing is a non-trivial task when enough information is not available for the entities in a KG. In this work, neural language models and a character embedding model are exploited to predict the type of an entity from only the name of an entity without any other information from the KG. The model has been evaluated on a benchmark dataset.