Zero-Shot Embedding for Unseen Entities in Knowledge Graph

Yu ZHAO  Sheng GAO  Patrick GALLINARI  Jun GUO  

Publication
IEICE TRANSACTIONS on Information and Systems   Vol.E100-D   No.7   pp.1440-1447
Publication Date: 2017/07/01
Publicized: 2017/04/10
Online ISSN: 1745-1361
DOI: 10.1587/transinf.2016EDP7446
Type of Manuscript: PAPER
Category: Artificial Intelligence, Data Mining
Keyword: 
zero-shot learning,  knowledge graph,  embedding learning,  relation prediction,  

Full Text: PDF>>
Buy this Article




Summary: 
Knowledge graph (KG) embedding aims at learning the latent semantic representations for entities and relations. However, most existing approaches can only be applied to KG completion, so cannot identify relations including unseen entities (or Out-of-KG entities). In this paper, motivated by the zero-shot learning, we propose a novel model, namely JointE, jointly learning KG and entity descriptions embedding, to extend KG by adding new relations with Out-of-KG entities. The JointE model is evaluated on entity prediction for zero-shot embedding. Empirical comparisons on benchmark datasets show that the proposed JointE model outperforms state-of-the-art approaches. The source code of JointE is available at https://github.com/yzur/JointE.