Knowledge graph entity typing via learning connecting embeddings

Knowledge graph (KG) entity typing aims at inferring possible missing entity type instances in KG, which is a very significant but still under-explored subtask of knowledge graph completion. In this paper, we propose a novel approach for KG entity typing which is trained by jointly utilizing local t...

Full description

Saved in:
Bibliographic Details
Published in:Knowledge-based systems 2020-05, Vol.196, p.105808, Article 105808
Main Authors: Zhao, Yu, Zhang, Anxiang, Feng, Huali, Li, Qing, Gallinari, Patrick, Ren, Fuji
Format: Article
Language:English
Subjects:
Embedding model
Entity typing
KG completion
Knowledge
Knowledge bases (artificial intelligence)
Knowledge graph
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Knowledge graph (KG) entity typing aims at inferring possible missing entity type instances in KG, which is a very significant but still under-explored subtask of knowledge graph completion. In this paper, we propose a novel approach for KG entity typing which is trained by jointly utilizing local typing knowledge from existing entity type assertions and global triple knowledge in KGs. Specifically, we present two distinct knowledge-driven effective mechanisms of entity type inference. Accordingly, we build two novel embedding models to realize the mechanisms. Afterward, a joint model via connecting them is used to infer missing entity type instances, which favors inferences that agree with both entity type instances and triple knowledge in KGs. Experimental results on two real-world datasets (Freebase and YAGO) demonstrate the effectiveness of our proposed mechanisms and models for improving KG entity typing.
ISSN:0950-7051
1872-7409
DOI:10.1016/j.knosys.2020.105808