摘要
针对传统文本分类系统的不足 ,提出了一种基于隐含语义索引的kNN的文本分类模型 .该方法既充分利用了向量空间模型在表示方法上的巨大优势 ,又弥补了其忽略语义的不足 ,具备一定的理论和现实意义 .
Because of the deficiency of traditional classification system,the text classification based on integrating k -nearest neighbor with latent semantic indexing was proposed. It took the advantage of abundant expression in Vector Space Model (VSM) and made up the shortage of less semantic information in VSM. The new scheme has significance both in theory and practice.
出处
《华中科技大学学报（自然科学版）》
EI
CAS
CSCD
北大核心
2004年第4期59-60,86,共3页
Journal of Huazhong University of Science and Technology(Natural Science Edition)
基金
国家高性能计算基金资助项目 (0 0 30 3)
关键词
文本分类
k最邻参照法
隐含语义索引
奇异值分解
text classification
k-nearnest neighbor
latent semantic indexing
singular value decomposition
