Research on semantic association pattern mining model based on ontology
Chao He, Yufeng Zhang · 2010
Most of text association pattern mining techniques transform texts into flat bags of words representation, which does not preserve sufficient semantics for the purpose of knowledge discovery. So the depth and accuracy of mining are not satisfying. In order to solve this problem, a novel ontology-based semantic association pattern mining model is proposed. The suggested model applies semantic role labeling to semantic analysis so that the semantic relations are able to be extracted precisely. For the defects of traditional association pattern mining algorithms that could not effectively deal with semantic metabase, a novel semantic-based association pattern mining algorithm is designed for the acquisition of the deep semantic association patterns from semantic metabase. Experimental results reveal that the new model can acquire deep semantic knowledge easily from text database and the algorithm mentioned above has strong adaptability and scalability.