Ontology auto-extension based on improved SVM algorithm

This paper researches on ontology auto-extension, which is a hot issue of semantic web. In this paper, technology related to information processing is used to automatically extend ontology instances from free text. Firstly, three tasks are identified after analyzing on ontology auto-extension. Secondly, a new binary tree (BT) is constructed based on the ontology taxonomy, and then it is used as the training and learning strategy of support vector machine (SVM) classifier. And the full strategy is regarded as Onto-BT-SVM model. The main advantage of this strategy is that the semantic of ontology is made full use of. Finally, Different multi-class classification strategies are compared to verify their impacts on classification effects. Experiment results show that the recall rate of Onto-BT-SVM model is 90.5% and the accuracy rate is 93.5%, which is satisfactory.