%0 Journal Article
%T 基于分布式表示的单步推理<br>Single-Step Inference Based on Distributed Representation
%A 万倩妮
%A 徐建良
%J Computer Science and Application
%P 553-563
%@ 2161-881X
%D 2020
%I Hans Publishing
%R 10.12677/CSA.2020.103057
%X <div style=\"text-align:justify;\">
	<span style=\"font-size:14px;\">目前，现有知识图谱大多存在信息缺失的问题，作为知识图谱关键技术之一的关系推理可以完成对数据关系的深入分析和挖掘，是知识图谱领域的研究热点。本文主要介绍了几种常用的基于分布式表示的单步推理算法，概述了算法的训练过程和评价指标，为今后该领域的研究提供参考借鉴。<br />
At present, most of the existing knowledge graphs have the problem of lack of information. As one of the key technologies of knowledge graph, relational inference can complete the indepth analysis and mining of data relations, which is a hot issue in the field of knowledge graph. This paper mainly introduces several common single step inference algorithms based on distributed representation, and describes the main process and evaluation index of the algorithm in order to provide reference for future research.</span> 
</div>
%K 分布式表示，单步推理，关系推理<br>Distributed Representation
%K Single Step Inference
%K Relation Inference
%U http://www.hanspub.org/journal/PaperInformation.aspx?PaperID=34791