本体映射的集成和语义挖掘研究

Research on Integration and Semantic Mining in Ontology Mapping

对于不同的待映射本体,各种映射策略的表现可能有较大差异,传统的映射方法并没有根据具体语境和策略的可信度进行映射结果集成,对产生的映射对也没有做进一步的语义挖掘。为了解决这个问题,根据本体和谐度对各策略权值进行自适应计算;利用结构语义信息进行语义传播(或利用在线本体作为背景知识)挖掘新的映射对。实验表明改进的方法可以明显提高查准率,获得更准确的映射结果。

Performance of different mapping strategies may be quite different when aligning different ontologies. Traditional mapping method could not compute the similarity based on the credibility of strategies and the dynamically change situation. And the output results also failed to enable further mining. To slove these problems, this paper presents an approach, which can adjust the weights automatically based on harmoniousness of ontologies. And this approach also provides new mapping sets by using semantically structural information or online ontologies as context knowledge. Experiment resuh shows that this algorithm improves the precision significantly and provides a better mapping result.