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

Thumbnail Image

Files

2020.deelio-1.11.pdf (510.79 KB)

Links to Files

https://www.aclweb.org/anthology/2020.deelio-1.11.pdf

Permanent Link

https://doi.org/10.18653/v1/2020.deelio-1.11
 http://hdl.handle.net/11603/20205

Collections

UMBC Computer Science and Electrical Engineering Department
UMBC Faculty Collection

Author/Creator

Author/Creator ORCID

Date

2020-11-19

Type of Work

conference papers and proceedings
Text

Department

Program

Citation of Original Publication

Rajat Patel and Francis Ferraro, On the Complementary Nature of Knowledge Graph Embedding, Fine Grain Entity Types, and Language Modeling, Proceedings of Deep Learning Inside Out (DeeLIO): The First Workshop on Knowledge Extraction and Integration for Deep Learning Architectures, pp 89-99, DOI: 10.18653/v1/2020.deelio-1.11

Rights

This item is likely protected under Title 17 of the U.S. Copyright Law. Unless on a Creative Commons license, for uses protected by Copyright Law, contact the copyright holder or the author.

Subjects

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.