On the Complementary Nature of Knowledge Graph Embedding, Fine Grain Entity Types, and Language Modeling
This work addresses the integration of structured and unstructured data for knowledge representation, but appears incremental as it builds on existing methods.
The authors tackled the problem of integrating knowledge graph embeddings, fine-grained entity types, and language modeling by showing that a language model-inspired approach improves both knowledge graph embeddings and entity type representations, and that joint modeling of structured knowledge and language yields mutual benefits.
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.