CLFLJul 21, 2020

Connecting Embeddings for Knowledge Graph Entity Typing

arXiv:2007.10873v11005 citations
Originality Incremental advance
AI Analysis

This addresses the under-explored subtask of knowledge graph completion, which is incremental as it builds on existing embedding methods for entity typing.

The paper tackles the problem of inferring missing entity types in knowledge graphs by proposing a novel approach that jointly utilizes local typing knowledge and global triple knowledge, demonstrating effectiveness on Freebase and YAGO datasets.

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 from 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 with 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. The source code and data of this paper can be obtained from: https://github.com/ Adam1679/ConnectE

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes