基于Apriori改进算法的局部反馈查询扩展  

Query Expansion of Local Feedback Based on Improved Apriori Algorithm

作　　者：陈燕红[1] 黄名选[2] 

机构地区：[1]广西大学物理学院,南宁530004 [2]广西教育学院数学与计算机系,南宁530023

出　　处：《现代图书情报技术》2007年第9期84-87,共4页New Technology of Library and Information Service

摘　　要：提出面向查询扩展的Apriori改进算法,采用三种剪枝策略,极大提高挖掘效率;针对现有查询扩展存在的缺陷,提出基于Apriori改进算法的局部反馈查询扩展算法,该算法用Apriori改进算法对前列初检文档进行词间关联规则挖掘,提取含有原查询词的词间关联规则,构造规则库,从库中提取扩展词,实现查询扩展。实验结果表明该算法能够提高信息检索性能,与现有算法比较,在相同查全率水平级下其平均查准率有了明显提高。An improved Apriori algorithm for query expansion is presented based on the thrice pruning strategy, This method can tremendously enhance the mining efficiency. After studying the limitations of existing query expansion, a novel query expansion algorithm of local feedback is proposed based on the improved Apriori algorithm, This algorithm can automatically mine those association rules related to original query in the top - rank retrieved documents using the improved Apriori algorithm, to construct an association rules - based database, and extract expansion terms related to original query from the database for query expansion. Experimental results show that our method is better than traditional ones in average precision.

关 键 词：查询扩展 APFIOFI算法 局部反馈 信息检索 

分 类 号：TP301.6[自动化与计算机技术—计算机系统结构]