| 摘要: |
| 在基于映射的数据交换系统框架下,提出了一种本体辅助的模式匹配方法.它利用WordNet词汇本体和决策树学习相结合的方法进行属性名称匹配,构建数据类型本体计算属性数据类型的语义距离,依赖领域本体发现一对多的语义匹配关系,这3个过程逐步提高了匹配质量.建立在实际应用数据上的实验结果表明,该方法具有较高的精确度和召回率. |
| 关键词: 模式匹配 本体 决策树学习 数据库 |
| DOI： |
| 分类号: |
| 基金项目:Supported by the National Natural Science Foundation of China under Grant No.60573126 (国家自然科学基金); the National High-Tech Research and Development Plan of China under Grant No.2004AA112010 (国家高技术研究发展计划(863)) |
|
| Ontology-Aided Automatic Schema Matching |
|
LIU Qiang,ZHAO Di,ZHONG Hua,HUANG Tao
|
| Abstract: |
| This paper introduces an ontology-aided schema matching method in the mapping-based data exchange framework. The decision tree learning and WordNet are used to match attribute names. A data type ontology is constructed to compute semantic distance between attribute data types. Also, domain ontologies can be used to detect 1:n semantic matches. The three steps improve the match quality steadily. Experiments of several real applications show encouraging results, yielding high precision and recall measures. |
| Key words: schema matching ontology decision tree learning database |
