检索规则说明:AND代表“并且”;OR代表“或者”;NOT代表“不包含”;(注意必须大写,运算符两边需空一格)
检 索 范 例 :范例一: (K=图书馆学 OR K=情报学) AND A=范并思 范例二:J=计算机应用与软件 AND (U=C++ OR U=Basic) NOT M=Visual
作 者:赵春晖 张俊[2] ZHAO Chunhui;ZHANG Jun(Information Retrieval and Knowledge Mining Laboratory,Wuhan University,Wuhan 430072,China;Shenzhen Securities Information Co.,Ltd,Shenzhen 518000,China)
机构地区:[1]武汉大学信息检索与知识挖掘研究所 [2]深圳证券信息有限公司
出 处:《情报工程》2018年第4期82-94,共13页Technology Intelligence Engineering
基 金:深圳市技术攻关资助项目证券信息多层网络数据检索与监控关键技术研究(JSGG20160229121006579)
摘 要:为了研究不同查询专指度语句的多样化检索效果,进而为提高检索质量和用户体验提供借鉴。本文基于TREC(2009-2012)Web Track检索词,人工进行专指度标注,选用语言模型狄利克雷平滑、语言模型线性差值平滑和TF-IDF三种模型,使用MAP-IA,α-nDCG@k,ERR-IA@k评价多样化检索结果,对检索结果进行统计学分析和差异性检验,全面分析了查询专指度与多样化检索效果之间的关联性。实验结果表明查询词的专指度特征与多样化检索的效果间存在一定的关联。强专指度查询的多样化检索效果要明显好于弱专指度查询,特别在靠前的检索结果列表中,这种差异性最大。In order to study the effectiveness of search diversification on queries with different specificity and improve retrieval quality and user experience, this paper manually labelled the specificity of queries from the TREC(2009-2012)Web Track, adopted the Dirichlet language model, linear interpolation language model and TF-IDF model, used the MAP-IA, α-nDCG@k, ERR-IA@k to evaluate diversified search results and performed statistical analysis and differential test on the results to comprehensively analyze the relationship between query specificity and search diversification. The experimental results showed that there was a certain correlation between the specificity feature of queries and the effect of diversified search. The diversified search results of the queries with stronger specificity were significantly better than those of the queries with narrower specificity, especially in the top search results list.
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在链接到云南高校图书馆文献保障联盟下载...
云南高校图书馆联盟文献共享服务平台 版权所有©
您的IP:216.73.216.222