一种结合结构化信息的富文本分类方法

AN APPROACH FOR RICH FORMAT TEXT CLASSIFICATION COMBINING WITH STRUCTURIZED INFORMATION

随着文本表现形式越来越丰富,文本分类研究的对象正从平文本逐渐转变为富文本,传统的平文本分类方法不能满足实际需要。分析了富文本中的结构化信息和文本内容信息,把它们作为两个重要的因素,综合考虑了其在分类中的作用,提出并实现了标签组件法、结构组件法和综合法三种富文本分类的方法。实验表明,所提出的方法有较好的分类表现,能解决OpenDocument的分类问题。

Conventional plain text classification methods can no longer meet the actual demands with the growing rich text representation, the research object of text classification has been changing gradually from plain text to rich format text. In the paper it puts forward the methods of label component classification, structurized component classification and combinative classification after analyzing two important factors, text content information and structurized information in rich format text, with synthetic consideration of their functions in classification. The implementation experiment indicates that the approach performs pretty well in classification and is good in solving classification problem of OpenDocument.