大本体的分块与映射方法研究

在本体的映射研究中，现实本体或大本体之间的映射算法是研究的难点。该文提出一种针对大层次本体的映射方法。根据本体的结构和概念之间的语义距离，应用向量空间模式（VSM）将概念表示成多维空间中的点。在此基础上，应用聚类算法（CURD）对概念进行聚类，形成若干个语义上相对独立的块，在2个本体的块之间根据参考点建立映射关系。实验结果表明，该方法在测试数据集上能得到较好的映射结果

Research on Large-scale Ontology Partition and Mapping Method

In research of ontology mapping,the mapping between real ontology or large-scale ontology is difficult.This paper proposes a mapping method for large class hierarchies,which is one kind of the large-scale ontologies.Based on ontology structure and semantic distance between classes,the classes can be put in a multi-dimension space by using Vector Space Model(VSM).Two large class hierarchies are partitioned into small blocks respectively by applying CURD clustering algorithm,and then blocks from different hie...