聚焦查询的自动文摘研究与实现  

Research and implementation of query-focused automatic summarization

作　　者：索红光[1] 安迪[1] 

机构地区：[1]中国石油大学计算机与通信工程学院,山东东营257061

出　　处：《计算机工程与应用》2010年第14期129-131,共3页Computer Engineering and Applications

摘　　要：聚焦查询的文摘把重点放在文档中用户关心的内容。聚焦查询的自动文摘方法以搜索引擎为问题查询工具,利用汉宁窗函数计算句子重要度,以体现问题与预期答案中的词密度特性。通过窗口从头到尾滑动来计算句子的权值选择出权值高的作为文摘。实验结果表明该方法形成的文摘优于Google文摘。Query-focused summarization laid emphasis on user＇s concern in the document.An approach to query-focused automatic summarization is presented.It utilizes search engine as tool for seeking answer.The importance of each sentence is computed by the Hanning window to take the density of words contained in the question and prospective answering account.Summarize a document by selecting the sentences with high weights as computed by moving a window from the beginning to the end of the document.Experimental results show that the summarization is better than Google＇s.

关 键 词：自动文摘 搜索引擎 汉宁窗 

分 类 号：TP31[自动化与计算机技术—计算机软件与理论]