Knowledge Graph Embedding Technology: A Review

Knowledge graph embedding (KGE) is a new research hotspot in the field of knowledge graphs, which aims to apply the translation invariance of word vectors to embedding entities and relationships of the knowledge graph into a low-dimensional vector space to complete knowledge representation. In this...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autor principal:	SHU Shitai, LI Song+, HAO Xiaohong, ZHANG Liping
Formato:	article
Lenguaje:	ZH
Publicado:	Journal of Computer Engineering and Applications Beijing Co., Ltd., Science Press 2021
Materias:	knowledge graph embedding (kge) knowledge representation knowledge graph completion (kgc) link prediction; triple classification Electronic computers. Computer science QA75.5-76.95
Acceso en línea:	https://doaj.org/article/9d173a393e8f46988ba16ca2d1d927de
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:9d173a393e8f46988ba16ca2d1d927de
record_format	dspace
spelling	oai:doaj.org-article:9d173a393e8f46988ba16ca2d1d927de2021-11-10T08:00:04ZKnowledge Graph Embedding Technology: A Review10.3778/j.issn.1673-9418.21030861673-9418https://doaj.org/article/9d173a393e8f46988ba16ca2d1d927de2021-11-01T00:00:00Zhttp://fcst.ceaj.org/CN/abstract/abstract2946.shtmlhttps://doaj.org/toc/1673-9418Knowledge graph embedding (KGE) is a new research hotspot in the field of knowledge graphs, which aims to apply the translation invariance of word vectors to embedding entities and relationships of the knowledge graph into a low-dimensional vector space to complete knowledge representation. In this paper, it is mainly concerned with the classification according to the types of practical problems to be solved. Firstly, it expounds four major types of embedding methods of knowledge graph, including deep learning-based methods, graphical features-based methods, translation model-based methods, and other model-based methods. The algorithm ideas of each model are elaborated, and the advantages and disadvantages of each model are concluded. Secondly, the algorithm experi-ment of knowledge graph embedding is analyzed and summarized from the four aspects of commonly used data sets, evaluation indicators, algorithms, and experiments, then a horizontal and vertical comparison of the embedding method is made. Finally, from the perspective of solving practical problems, the future direction of knowledge graph embedding technology is given. Through research, it is discovered that in the deep learning-based method, LCPE achieves the best effect; in the graphical features-based method, TCE makes the best impression; whereas in the translation model-based method, NTransGH responds most optimistically. Future researches can be expanded on the basis of LCPE, TCE, and NTransGH to continuously improve the experimental effects of link prediction and triplets classification.SHU Shitai, LI Song+, HAO Xiaohong, ZHANG LipingJournal of Computer Engineering and Applications Beijing Co., Ltd., Science Pressarticleknowledge graph embedding (kge)knowledge representationknowledge graph completion (kgc)link prediction; triple classificationElectronic computers. Computer scienceQA75.5-76.95ZHJisuanji kexue yu tansuo, Vol 15, Iss 11, Pp 2048-2062 (2021)
institution	DOAJ
collection	DOAJ
language	ZH
topic	knowledge graph embedding (kge) knowledge representation knowledge graph completion (kgc) link prediction; triple classification Electronic computers. Computer science QA75.5-76.95
spellingShingle	knowledge graph embedding (kge) knowledge representation knowledge graph completion (kgc) link prediction; triple classification Electronic computers. Computer science QA75.5-76.95 SHU Shitai, LI Song+, HAO Xiaohong, ZHANG Liping Knowledge Graph Embedding Technology: A Review
description	Knowledge graph embedding (KGE) is a new research hotspot in the field of knowledge graphs, which aims to apply the translation invariance of word vectors to embedding entities and relationships of the knowledge graph into a low-dimensional vector space to complete knowledge representation. In this paper, it is mainly concerned with the classification according to the types of practical problems to be solved. Firstly, it expounds four major types of embedding methods of knowledge graph, including deep learning-based methods, graphical features-based methods, translation model-based methods, and other model-based methods. The algorithm ideas of each model are elaborated, and the advantages and disadvantages of each model are concluded. Secondly, the algorithm experi-ment of knowledge graph embedding is analyzed and summarized from the four aspects of commonly used data sets, evaluation indicators, algorithms, and experiments, then a horizontal and vertical comparison of the embedding method is made. Finally, from the perspective of solving practical problems, the future direction of knowledge graph embedding technology is given. Through research, it is discovered that in the deep learning-based method, LCPE achieves the best effect; in the graphical features-based method, TCE makes the best impression; whereas in the translation model-based method, NTransGH responds most optimistically. Future researches can be expanded on the basis of LCPE, TCE, and NTransGH to continuously improve the experimental effects of link prediction and triplets classification.
format	article
author	SHU Shitai, LI Song+, HAO Xiaohong, ZHANG Liping
author_facet	SHU Shitai, LI Song+, HAO Xiaohong, ZHANG Liping
author_sort	SHU Shitai, LI Song+, HAO Xiaohong, ZHANG Liping
title	Knowledge Graph Embedding Technology: A Review
title_short	Knowledge Graph Embedding Technology: A Review
title_full	Knowledge Graph Embedding Technology: A Review
title_fullStr	Knowledge Graph Embedding Technology: A Review
title_full_unstemmed	Knowledge Graph Embedding Technology: A Review
title_sort	knowledge graph embedding technology: a review
publisher	Journal of Computer Engineering and Applications Beijing Co., Ltd., Science Press
publishDate	2021
url	https://doaj.org/article/9d173a393e8f46988ba16ca2d1d927de
work_keys_str_mv	AT shushitailisonghaoxiaohongzhangliping knowledgegraphembeddingtechnologyareview
_version_	1718440401576132608

Knowledge Graph Embedding Technology: A Review

Ejemplares similares