Knowledge Graph Completion: A Review

Дополнение графов знаний: обзор
Zongtao Duan, Zhe Chen, Yuehan Wang, Bin Zhao, Jing Cheng, Xin Zhao
2020-01-01

knowledge graph completionknowledge graph constructionmissing entity predictionrepresentation learningrule-based reasoning
Knowledge graph completion (KGC) is a hot topic in knowledge graph construction and related applications, which aims to complete the structure of knowledge graph by predicting the missing entities or relationships in knowledge graph and mining unknown facts. Starting from the definition and types of KGC, existing technologies for KGC are analyzed in categories. From the evolving point of view, the KGC technologies could be divided into traditional and representation learning based methods. The former mainly includes rule-based reasoning method, probability graph model, such as Markov logic network, and graph computation based method. The latter further includes translation model based, semantic matching model based, representation learning based and other neural network model based methods. In this article, different KGC technologies are introduced, including their advantages, disadvantages and applicable fields. Finally the main challenges and problems faced by the KGC are discussed, as well as the potential research directions.
1
KGC technologies are categorized evolutionarily into traditional methods and representation-learning-based methods.
2
Knowledge graph completion predicts missing entities or relationships to complete graph structure and discover unknown facts.
3
Representation-learning approaches include translation models, semantic-matching models, other representation-learning techniques, and neural-network-based methods.
4
The review compares methods’ advantages, disadvantages, application fields, challenges, and potential future research directions.
5
Traditional approaches include rule-based reasoning, probabilistic graphical models such as Markov logic networks, and graph-computation methods.

Knowledge graph completion (KGC) task/system

methods, advantages, disadvantages, applicability, challenges, and future directions for predicting missing entities or relationships and mining unknown facts

Publication Details
Publication Date
2020-01-01
Journal
Publisher
ISSN
Cited by
351
Access Type
Author Information
Authors
Zongtao Duan
Zhe Chen
Yuehan Wang
Bin Zhao
Jing Cheng
Xin Zhao
Explore further
Open the scid.ai AI chat with a ready-made request: it will find papers on a similar topic and help build a literature review.
Find similar papers in the chat →
Make a presentation
100%