迭代拉普拉斯半监督学习本体算法

An ontology algorithm based on iterated Laplacian semi-supervised learning

本体相似度计算和本体映射是知识表示和信息处理的核心研究内容。利用迭代拉普拉斯半监督学习方法将本体图中每个顶点映射成一个实数,通过比较顶点对应实数间的差值得到本体相似度计算算法和本体映射策略。通过两个实验表明,该方法对特定的应用领域是有效的。

Ontology similarity measure and ontology mapping are central contexts for knowledge representation and information processing.An ontology algorithm based on iterated Laplacian semi-supervised learning is proposed.Using iterated Laplacian semi-supervised learning method,all the vertices of the ontology graph are mapped into real numbers.Then,the ontology similarity measure algorithm and the ontology mapping strategy are obtained by comparing the differences of their corresponding values.Two experiments confirm that the new algorithm has high quality for special application fields.