基于主题向量模型的多样化资源选择算法  

Topic vector model based resource selection algorithm for diversification

作　　者：李亮 张芳[2] LI Liang;ZHANG Fang(School of Computer Science and Communication Engineering,Jiangsu University,Zhenjiang 212013,Jiangsu Province,China;School of Computer and Information Engineering,Nanyang Institute of Technology,Nanyang 473000,Henan Province,China)

机构地区：[1]江苏大学计算机科学与通信工程学院,江苏镇江212013 [2]南阳理工学院计算机与信息工程学院,河南南阳473000

出　　处：《信息技术》2018年第9期79-83,共5页Information Technology

基　　金：江苏省自然科学基金项目(BK20171303)

摘　　要：检索结果多样化任务下的资源选择是联邦检索的重要研究内容。针对现有显式方法的信息依赖和隐式方法的多样化性能不高,提出在α相关度筛选后得到的相关文档集上,构建子主题向量模型。从文中语义层提取数据源内容特征,提升资源相似度计算准确度,实现多样化的资源选择。实验显示,基于主题向量模型的资源选择方法表现出更好的性能。Resource selection under the diversified tasks of search results is an important research topic in federal search. The information-dependent for explicit methods and poor performance for the existing implicit methods,a sub-topic vector model is proposed based on the relevant documents obtained after theα-correlation filtering. It extracts the content characteristics of data sources from the textual semantic layer,enhances the accuracy of resource similarity calculation and diversifying resource selection. The experiments show that the resource selection method based on the topic vector model has better performance.

关 键 词：主题向量模型 资源相似度 联邦检索 资源选择 检索结果多样化 

分 类 号：TP391.3[自动化与计算机技术—计算机应用技术]