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

Rajat Patel, Francis Ferraro


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.
Anthology ID:
2020.deelio-1.11
Volume:
Proceedings of Deep Learning Inside Out (DeeLIO): The First Workshop on Knowledge Extraction and Integration for Deep Learning Architectures
Month:
November
Year:
2020
Address:
Online
Editors:
Eneko Agirre, Marianna Apidianaki, Ivan Vulić
Venue:
DeeLIO
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
89–99
Language:
URL:
https://aclanthology.org/2020.deelio-1.11
DOI:
10.18653/v1/2020.deelio-1.11
Bibkey:
Cite (ACL):
Rajat Patel and Francis Ferraro. 2020. On the Complementary Nature of Knowledge Graph Embedding, Fine Grain Entity Types, and Language Modeling. In Proceedings of Deep Learning Inside Out (DeeLIO): The First Workshop on Knowledge Extraction and Integration for Deep Learning Architectures, pages 89–99, Online. Association for Computational Linguistics.
Cite (Informal):
On the Complementary Nature of Knowledge Graph Embedding, Fine Grain Entity Types, and Language Modeling (Patel & Ferraro, DeeLIO 2020)
Copy Citation:
PDF:
https://aclanthology.org/2020.deelio-1.11.pdf
Video:
 https://slideslive.com/38939734
Code
 rajathpatel23/joint-kge-fnet-lm
Data
FIGER