An important problem that the text information filtering technology needs to solve is the formal handling of documents,which makes the text become computable and reasoning information.

• 文本信息过滤技术需要解决的一个重要问题是对文档进行形式化处理,使得文本成为可计算和推理的信息,而中文自动分词是中文信息处理的基础性工作。