On the Complementary Nature of Knowledge Graph Embedding, Fine Grain Entity Types, and Language Modeling

TL;DR

This paper explores how combining neural knowledge graph embeddings, fine-grain entity types, and language modeling enhances the quality of knowledge representations and entity typing.

Contribution

It introduces a language model-inspired approach that improves knowledge graph embeddings and entity type representations through joint modeling.

Findings

Language model-inspired embeddings outperform traditional methods.

Joint modeling enhances both knowledge graph and language understanding.

Improved fine-grain entity type prediction accuracy.

Abstract

We demonstrate the complementary natures of neural knowledge graph embedding, fine-grain entity type prediction, and neural language modeling. We show that a language model-inspired knowledge graph embedding approach yields both improved knowledge graph embeddings and fine-grain entity type representations. Our work also shows that jointly modeling both structured knowledge tuples and language improves both.