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.
出处
《湖南城市学院学报（自然科学版）》
CAS
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)
关键词
TextRank
信息抽取
摘要算法
累计贡献率
TextRank
information extraction
summation algorithm
accumulating contribution rate
