XTM的主题相关度的量化机制研究  

Research on Degree of Topic Relatedness in XTM

作　　者：裘江南[1] 姚永祥[1] 仲秋雁[1] 

机构地区：[1]大连理工大学管理学院,大连116024

出　　处：《情报学报》2007年第3期332-338,共7页Journal of the China Society for Scientific and Technical Information

基　　金：国家社会科学基金（批准号：06BTQ026）;辽宁省自然科学基金（批准号：2051066）

摘　　要：主题图XTM作为一种用于描述信息资源知识结构的工具，在信息和知识资源的整合领域有着广泛的应用前景。然而，在XTM技术框架中只定义了主题之间的关联，并没有给出相应的相关度评价方法，而且关联只局限在彼此有直接关联的主题之间，并没有定义间接关联。因此有必要为主题图引人相关度的评价，进而更清晰地理解主题图的语义结构。针对这一问题，本文在对XTM中主题关联语义结构的分析的基础上，通过划分主题关联种类，从XTM抽取出其树形的语义层次结构。在此树形结构的基础上，引人语义距离的概念进行对主题图的二级关联扩展和关联间语义相关度的计算。并在在相关算例的验证过程中，得到了较好的计算结果。With a purpose to convey knowledge about resources through a superimposed layer, or map, of the resources, XTM （XML Topic Map） is very premising in the field of integrating information and knowledge resources. According to the Specification of XML, associations between the topics are defined, but there are no corresponding evaluating methods. What＇s more there are only direct associations, and indirect ones are not defined. So it＇s necessary to evaluate the degree of topic relative in order to understand the semantic structure of the Topic Map more clearly. For this, based on analyses of topic relative semantic structure, a tree-structure semantic architecture is extracted from XTM by dividing the type of topic association. Semantic distance is introduced in this paper to expand the second level association and calculate the degree of topic relative. In the validate example of this method, get a good result.

关 键 词：XTM 二级关联扩展 相关度 

分 类 号：G250.73[文化科学—图书馆学]