基于语义互补推理的文献隐含知识的发现方法研究  

Research on Discovery Method in Literature Implicit Knowledge Using Semantic Complementary Reasoning

作　　者：温浩[1] 温有奎[2] 

机构地区：[1]西安建筑科技大学信息与控制学院,西安710055 [2]西安电子科技大学经济管理学院,西安710071

出　　处：《计算机科学》2014年第6期171-175,共5页Computer Science

摘　　要：文献知识发现已经成为解决海量信息检索难题的突破技术。但是目前的文献知识发现方法是基于词袋法的矢量空间模型方法。这类方法具有词汇元素之间语义无关性的先天不足,不能有效地发现文本之间存在的大量潜在知识。提出一种基于主谓宾(S,P,O)结构的最小知识单元表示及其语义推理的中文文献知识发现方法,避免了传统的文献知识发现方法的不足,并在此模型的基础上提出了一种推理算法,其能有效地发现文本中的潜在知识。经过实验证明,该方法与传统的文献知识发现方法相比有效地提高了潜在知识发现的正确率。The literature knowledge discoveries methods have become the breakthrough technologies to solve the difficult problem of massive information retrieval.But the current literature knowledge discovery methods are vector space methods based on word bag.This methods have congenital deficiency,i.e.semantic independence between vocabulary elements,so a large number of potential knowledge which exists between texts can＇t be discovered.Therefore,a new Chinese literature knowledge discovery method is put forward in this paper.The representation of the minimum knowledge unit and the semantic reasoning are based on subject predicate object （S,P,O） structure in this method.So the deficiency of traditional knowledge discovery method can be avoided,and a reasoning algorithm is proposed based on the structure to discover the potential knowledge between texts.The efficiency of discovering the potential of knowledge of our method is enhanced in contrast to the traditional methods,which is proved by the experiments in this paper.

关 键 词：文本知识发现 语义互补推理 知识单元挖掘 

分 类 号：TP311[自动化与计算机技术—计算机软件与理论]