关键词: 公文分类, Bootstrapping, 随机关键词产生, 贝叶斯方法

Abstract: Design and implementation of a government official document classification system with topic phrase were presented. This system fully considered the value of topic phrase in the classification preprocessing, and made feature space transformation and dimension reduction by the stochastic keyword generation and the Bootstrapping. It differed from the traditional text classification preprocessing, and the performance of the official document classification system was improved. Official document classification using stochastic keyword generation outperforms other methods.

Key words: official document classification, Bootstrapping, stochastic keyword generation, Naï, ve Bayes