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.
@article{arxiv.2010.05732,
title = {On the Complementary Nature of Knowledge Graph Embedding, Fine Grain Entity Types, and Language Modeling},
author = {Rajat Patel and Francis Ferraro},
journal= {arXiv preprint arXiv:2010.05732},
year = {2020}
}
Comments
To appear at the EMNLP 2020 Workshop on Deep Learning Inside Out