|
|||||
|
|
| 基于小生境混合遗传算法的文本特征词聚类研究 | |
| 引用本文： | 戴文华,何婷婷,焦翠珍.基于小生境混合遗传算法的文本特征词聚类研究[J].计算机科学,2008,35(1):202-203. |
| 作者姓名： | 戴文华 何婷婷 焦翠珍 |
| 作者单位： | 1. 华中师范大学计算机科学系,武汉,430079;咸宁学院计算机系,咸宁,437000 2. 华中师范大学计算机科学系,武汉,430079 3. 咸宁学院计算机系,咸宁,437000 |
| 基金项目： | 咸宁学院校科研和教改项目 , 国家自然科学基金 , 国家社会科学基金 , 教育部科学技术研究重点项目 |
| 摘 要： | 提出一种基于小生境混合遗传算法的文本特征词聚类方法.该方法首先采用贝叶斯语义模型对语料库进行统计分析,并以K-L距离度量特征词间的距离,然后将小生境遗传算法与K-Means算法相结合,对文本特征词进行聚类,为文本特征词聚类提供了较高的效率和精确度.实验表明该方法是一种高效可行的文本特征词聚类方法. |
| 关 键 词： | 小生境 遗传算法 K-L距离 K-means聚类 特征词聚类 |
Research of Text Feature Words Clustering Based on Niche Hybrid Genetic Algorithm |
|
| DAI Wen-Hua,HE Ting-Ting,JIAO Cui-Zhen.Research of Text Feature Words Clustering Based on Niche Hybrid Genetic Algorithm[J].Computer Science,2008,35(1):202-203. | |
| Authors: | DAI Wen-Hua HE Ting-Ting JIAO Cui-Zhen |
| Abstract: | Combined with the global optimization ability of Niche Genetic Algorithm and the efficiency of K-Means Algorithm,a new Text Feature Words Clustering method based on Niche Hybrid Genetic Algorithm is proposed.This method first uses the Bayesian Semantics Model to carry out statistical analysis on the corpus.K-L distance is used for measuring distances between feature words.Using this method,we can provide a higher efficiency and precision for Text Feature Words Clustering.Experiments indicate that Niche Hybrid Genetic Algorithm is an effective and feasible method for Text Feature Words Clustering. |
| Keywords: | Niche Genetic algorithm K-L distance K-means clustering Feature words clustering |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ | |
| 点击此处可从《计算机科学》下载全文 | |
