Skip to Main Content
In the theory of knowledge, quantificational measurement of knowledge is of great importance. Meanwhile, how to acquire knowledge automatically has become the bottleneck of ontology-building. In this paper, we first introduce methods of semantic measurement, and propose an algorithm on semantic similarity from the concept of information content of nodes in WordNet. Our method concerns with the polysemous words filtering out irrelevant meaning, and incorporating verbs for similarity calculation. Using the results of similarity measurement, we carry out an ontology-based extraction from the Web page and finally obtain a solution to the problem of knowledge acquisition.