Using the result of word segmentation we give a comprehensive feature weight calculation and we get the feature words set.
对分词的结果再进行综合加权处理,最终得到文档的特征概念集。
Both of the algorithms based on the context of feature words in sentence of training texts can get a set of feature words that identify the category of a text.
该算法依据训练文本集的特征词句子环境,获取识别文本主题类别的特征词集合。
应用推荐