改进的TextRank双层单文档摘要提取算法  

Improved TextRank Double Layers Single-document Summation Extracting Algorithm

作　　者：何春辉 李云翔[2] 王孟然 王梦贤 

机构地区：[1]湘潭大学数学与计算科学学院,湖南湘潭411105 [2]湖南城市学院理学院,湖南益阳413000 [3]长沙县印山学校,长沙410135 [4]湖南城市学院管理学院,湖南益阳413000

出　　处：《湖南城市学院学报（自然科学版）》2017年第6期55-60,共6页Journal of Hunan City University:Natural Science

基　　金：益阳市科技计划项目(2014JZ40)

摘　　要：本文提出了基于句子重要度的累积贡献率摘要句筛选算法和改进的TextRank双层单文档摘要提取算法﹒摘要提取算法采用了分层结构,在不同层上融合了基于句子重要度的累积贡献率摘要句筛选算法,同时使用了长句和短句两种不同分割方式相结合的策略来构建摘要提取算法﹒用手工整理的中文单文档摘要数据集验证了算法的性能,结果表明:提取的摘要质量非常好﹒A summation sentence selection algorithm based on accumulating contribution rate of sentence importance and an improved TextRank double layers single-document summation extraction algorithm are proposed in this paper. The summation extraction algorithm adopts the hierarchical structure, on the different layer, the summation sentence selection algorithm based on accumulating contribution rate of sentence importance is blended, at the same time, using long sentences and short sentences in two different ways to construct summation extraction algorithm. The manual finishing Chinese single-document summation data set is used to verify the performance of the algorithm, the results show that the quality of the extraction summation is very fine.

关 键 词：TextRank 信息抽取 摘要算法 累计贡献率 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]