一种基于主题划分及TF-IDF的文本摘要提取方法  

An Extraction Method of Text Summarization Based on Topic Partition and TF-IDF

作　　者：朱小虎 周艳平[1] 姜涛 陈显利[1] ZHU Xiaohu;ZHOU Yanping;JIANG Tao;CHEN Xianli(College of Information Science and Technology,Qingdao University of Science&Technology,Qingdao 266061)

机构地区：[1]青岛科技大学信息科学技术学院,青岛266061

出　　处：《计算机与数字工程》2022年第8期1760-1765,共6页Computer & Digital Engineering

摘　　要：提取作为自然语言处理领域的一项重要任务,是解决信息过载和冗余的有效方法。论文提出了一种基于主题划分及TF-IDF(词频-逆文本频率指数)的文本摘要提取方法,该方法首先将文本段落进行主题划分,其次使用TF-IDF算法对不同主题的文本抽取中心句,最后将各个主题的中心句按顺序合并成文本摘要。将论文提出的文本摘要提取方法分别在知网论文数据集和DUC公共数据集上进行了仿真实验,并和传统方法进行相比分析,实验结果表明,论文提出的方法能有效地提高文本摘要提取的准确性,并且有更好的适应性。As an important task in the field of natural language processing,text Abstract extraction is an effective method to solve information overload and redundancy. In this paper,a text Abstract extraction method based on topic partition and TF-IDF(word frequency inverse text frequency index)is proposed. Firstly,the text paragraphs are divided into topics. Secondly,the TF-IDF algorithm is used to extract the central sentences of different topics. Finally,the center sentences of each topic are merged into text summaries in order. The method proposed in this paper is simulated on HowNet paper data set and Duc public data set,and compared with the traditional method,the experimental results show that the proposed method can effectively improve the accuracy of text Abstract extraction,and has better adaptability.

关 键 词：文本摘要 主题划分 TF-IDF 中心句提取 

分 类 号：TP391.6[自动化与计算机技术—计算机应用技术]