潜在语义分析聚类算法在文摘句子排序中的应用  

Application of latent semantic analysis clustering algorithm in summary sentence ordering

作　　者：郭红建[1] 黄兵[1] 

机构地区：[1]南京审计学院信息科学学院,南京211815

出　　处：《计算机应用研究》2013年第11期3299-3301,共3页Application Research of Computers

基　　金：国家自然科学基金资助项目(61170105);江苏省公共工程审计重点实验室2012年开放课题(20201201211)

摘　　要：针对多文档文摘生成过程中话题容易中断和文摘句子语义出现不连贯这两个研究难点,分析了潜在语义分析聚类算法在句子排序中的应用,以期提高文摘的生成质量。先采用潜在语义分析聚类算法将文摘句子聚类,从而形成话题集,以达到解决话题中断的目的。通过计算文档的文摘展现力,挑选出文摘展现力最大的文档作为模板,然后根据模板对文摘句子进行两趟排序。实验结果表明,提出的算法是有效的,该算法能够提高文摘的可读性。In order to improve the performance of summarization, this paper researched on application of latent semantic analysis clustering algorithm in summary sentence ordering. It adopted latent semantic analysis clustering algorithm to cluster summary sentences into topic sets to make the sentences within the same topic without be interrupted. It selected the ordering template by the summary representation of document, and ordered topic sets by the relational position in the template, ordered the sentences in the same topic set by the position in template. The experimental result shows that the proposed method is effective. It improves the readability of the summary.

关 键 词：多文档文摘 聚类 句子排序 

分 类 号：TP301[自动化与计算机技术—计算机系统结构]