A Survey of Knowledge Reasoning based on KG

2019 2nd International Conference on Advanced Materials, Intelligent Manufacturing and Automation

Lu, Rui^1 ; Cai, Zhiping^2 ; Zhao, Shan^2

Unit 73089, Xuzhou, Jiangsu

221007, China^1

College of Computer, National University of Defense Technology, Changsha, Hunan

41008, China^2

关键词: Future improvements;    Inference models;    Knowledge graphs;    Knowledge reasoning;    Look-forward;    NAtural language processing;    Question Answering;   

Others  :  https://iopscience.iop.org/article/10.1088/1757-899X/569/5/052058/pdf
DOI  :  10.1088/1757-899X/569/5/052058

来源: IOP

【 摘 要 】

Knowledge Reasoning(KR) has become the core issue in the field of Artificial Intelligence(AI) and even Natural Language Processing(NLP). KR based on Knowledge Graph(KG) is based on existing KG's facts. It uses some inference models and algorithms to infer new unknown knowledge and targets at improving the completeness and accuracy of KG. This article presents a brief overview of KR based on KG, expounds the connotation and research scope of it, judges the two main research directions(Knowledge Graph Completion(KGC) and Question Answering over Knowledge Graph (QA-KG)) of current KR and summarizes the four main technical methods. A series of latest results of current research on KR are also listed in this paper. Finally, we look forward to the future improvement of KR.