| 汉语文献文外频率加权与逆文献频率加权方法的比较 |
| |
| 引用本文： | 王超,黄水清,杨小莉.汉语文献文外频率加权与逆文献频率加权方法的比较[J].情报理论与实践,2007,30(2):275-277,202. |
| |
| 作者姓名： | 王超 黄水清 杨小莉 |
| |
| 作者单位： | 南京农业大学,信息科学技术学院,江苏,南京,210095 |
| |
| 摘 要： | 本文针对信息表示和信息检索中的文外频率加权和逆文献频率加权进行定量分析。以《软件学报》2004年发表的166篇计算机类的文献为测试集，通过计算机切词，统计词频，分别计算出各种语词加权方式不同的权重，并进行比较分析，得出了逆文献频率加权优于文外频率加权法，对文献频率取对数的逆文献频率加权公式优于不取对数的加权公式的结论。
|
| 关 键 词： | 信息检索 加权算法 语词加权 逆文献频率加权 |
| 修稿时间： | 2006-10-09 |
Comparison of Out Document Frequency Weight Method with Inverse Document Frequency Weight Method for Chinese Documents |
| |
| Wang Chao et al..Comparison of Out Document Frequency Weight Method with Inverse Document Frequency Weight Method for Chinese Documents[J].Information Studies:Theory & Application,2007,30(2):275-277,202. |
| |
| Authors: | Wang Chao |
| |
| Institution: | Wang Chao et al. |
| |
| Abstract: | A quantitative analysis of the out document frequency weight and inverse document frequency weight used in information representation and information retrieval is given. With the 166 literatures on computers published in The Journal of Software in 2004 as the test set, this article calculates the weight of different word weighting methods and makes a comparative analysis by cutting words and counting word frequency with the computer. It comes to the conclusion that the diverse document frequency weight is better than the out document frequency weight, and the formula of the inverse document frequency weight with logarithm is better than that without logarithm. |
| |
| Keywords: | information retrieval weight algorithm word weight inverse document frequency |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
