基于话题相关的文档集的无向基本要素网络的连通性探讨  

Connectivity of Undirected Basic Element Network Constructed on Document Set of Topic-related Document

作　　者：杨华[1,2] 姬东鸿[3] 陈波[3,4] 

机构地区：[1]贵州师范大学数学与计算机科学学院,贵州贵阳550001 [2]武汉大学文学院,湖北武汉430072 [3]武汉大学计算机学院,湖北武汉430072 [4]湖北文理学院文学院,湖北襄阳441053

出　　处：《中文信息学报》2015年第4期103-110,共8页Journal of Chinese Information Processing

基　　金：国家自然科学基金项目(61070243);国家社科基金重大项目(11&ZD189);贵州省高层次人才科研项目(TZJF-2010年048号);贵州省科教青年英才培养工程项目("黔省专合字(2012)155号");贵州师范大学博士科研启动基金项目(11904-05032110011);中国博士后科学基金项目(2013M531730)

摘　　要：基于数量有限的文档,该文构建以基本要素中的head和modifier为节点的无向网络UBEN,调查了话题相关文档的UBEN的连通性,指出了话题相关的文档的UBEN具有的特性。讨论停用词对UBEN连通性的影响,比较了相关文档集和随机文档集的UBEN的联通特性的差异,指出了连通性在一定程度上是文档之间内容相关导致的融合结果。结论对多文档自动文摘和信息检索等任务有一定的意义。Based on relatively limited number of documents, undirected basic element networks （UBEN）, in which nodes are header or modifier, are constructed. The connectivity of UBEN constructed on topic-related documents is investigated and the stopwords influence on connectivity is discussed. Furthermore, the connectivity difference be- tween UBENs respectively constructed on topic-related documents and randomly-selected documents are contrasted. It is pointed out that connectivity of UBEN construced on topic-related documents are resulted from information fu- sion of the topic-related documents on some level, instead of from property of language only. This conclusion is of some significance for some natural language processing tasks, such as automatic summarization, information retrieval, etc.

关 键 词：话题相关文档集 自动文摘 复杂网络 连通性 信息融合 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]