首页 | 本学科首页   官方微博 | 高级检索  
     

基于实体关系网络的微博文本摘要
引用本文:薛竹君,杨树强,束阳雪.基于实体关系网络的微博文本摘要[J].计算机科学,2016,43(9):77-81.
作者姓名:薛竹君  杨树强  束阳雪
作者单位:国防科学技术大学计算机学院 长沙410073,国防科学技术大学计算机学院 长沙410073,国防科学技术大学计算机学院 长沙410073
基金项目:本文受国家863高技术研究发展计划(2012AA01A401)资助
摘    要:在解析 微博文本语法的基础上,结合实体关系的定义和形式化表示,提出了采用关系网络有向图模型的方法来反映文本之间的结构关系,较好地表达了文本的语义信息,弥补了词频特征刻画的不足之处。利用改进后的TPR(Topic-PAGERANK)测算各节点对应的度来表现关系元组的重要程度,按序输出关系元组对应的原博文语义字段作为摘要。最后,通过实验证明了基于关系网络的文本自动文摘方法抽取出的摘要涵盖信息更全面,冗余更少。

关 键 词:实体关系  短文本  文本表示  语法分析  Topic-PAGERANK
收稿时间:7/1/2015 12:00:00 AM
修稿时间:2015/8/22 0:00:00

Microblog Text Summarization Based on Entity Relation Network
XUE Zhu-jun,YANG Shu-qiang and SHU Yang-xue.Microblog Text Summarization Based on Entity Relation Network[J].Computer Science,2016,43(9):77-81.
Authors:XUE Zhu-jun  YANG Shu-qiang and SHU Yang-xue
Affiliation:College of Computer,National University of Defense Technology,Changsha 410073,China,College of Computer,National University of Defense Technology,Changsha 410073,China and College of Computer,National University of Defense Technology,Changsha 410073,China
Abstract:On the basis of syntax parsing,combining the definition of entity relationship and formalized representation,this paper put forward a method based on directed graph model to reflect the structured relationship between texts,expressing text semantic information,making up for the shortcomings of word frequency characteristics.After that,the corresponding value of each node is measured with improved TPR (Topic-PAGERANK) to represent the importance of the relationship group.Then the corresponding original microblog text of relational tuples is sequentially outputed.Finally,it is proved by experiments that the text summarization extracted by automatic text summarization method based on relational tuple is more comprehensive and less redundant.
Keywords:Entity relationship  Short text  Text expression  Syntax parsing  Topic-PAGERANK
点击此处可从《计算机科学》浏览原始摘要信息
点击此处可从《计算机科学》下载全文
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