首页 | 本学科首页   官方微博 | 高级检索  
     

中文信息检索中二元文法索引策略的改进
引用本文:韩中元,韩咏,马威,崔硕.中文信息检索中二元文法索引策略的改进[J].微计算机信息,2010(15).
作者姓名:韩中元  韩咏  马威  崔硕
作者单位:黑龙江工程学院计算机科学与技术系;电子科技大学;澳门理工大学;
基金项目:黑龙江省教育厅科学技术项目;基金申请人:韩中元;项目名称:中文信息检索中索引策略的研究(11531304)
摘    要:本文将部分语义信息加入到二元文法中,提出改进的二元文法索引策略。本文应用2-泊松模型的BM25公式在TREC公开数据集上进行了测试。实验表明,改进的二元文法索引策略与基于字的索引策略、基于词的索引策略和基于二元文法的索引策略对比,在主要性能评测参数平均精确率、R-精确率参数上相对较优。

关 键 词:中文信息检索  索引策略  二元文法  

The improved bigram indexing strategy for Chinese Information Retrieval
HAN Zhong-yuan HAN Yong MA Wei CUI Shuo.The improved bigram indexing strategy for Chinese Information Retrieval[J].Control & Automation,2010(15).
Authors:HAN Zhong-yuan HAN Yong MA Wei CUI Shuo
Affiliation:HAN Zhong-yuan HAN Yong MA Wei CUI Shuo(Department of Computer Science , Technology,Heilongjiang Institute of Technology,Harbin,150050,China)(School of Computer Science , Engineering,University of Electronic Science , Technology of China,Chengdu,610054,China)(Macao Polytechnic Institute,School of Public Administration,Macao,China,999078,China)
Abstract:This paper focuses on the indexing strategy for Chinese Information Retrieval(IR).The improved bigram indexing strategy is put forward by adding semantic information into bigram.2-Possion Model,the classical probabilistic retrieval model,is used as retrieval model.The effectiveness of the new approach is evaluated on TREC Mandarin corpus.Experimental results show that the improved bigram indexing strategy achieves better than the traditional indexing unite,i.e.character,word and bigram,by the measurement of...
Keywords:Chinese information retrieval  indexing strategy  bigram  
本文献已被 CNKI 等数据库收录!
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号