基于文本多维度特征的自动摘要生成方法

doi:10.19678/j.issn.1000-3428.0055047

摘要/Abstract

摘要： 现有长文本自动摘要生成方法存在句子特征单一化和无法全面衡量句子相似特征的问题，导致摘要生成的准确率降低。为此，提出一种基于图集成模型的自动摘要生成方法。在计算得到文本句子词频、语义和句法特征后，利用朴素贝叶斯方法将文本多维度特征的融合问题转化为图集成方式，提高句子间相似计算的准确性，并在此基础上通过TextRank算法生成文本摘要。实验结果表明，相比传统基于序列到序列模型的摘要生成方法和基于句子多维特征的摘要抽取方法，该方法取得了更高的ROUGE指标值，能够有效综合句子的多维特征，提高摘要生成的准确率。

关键词: 句子相似度, 图集成模型, 文本摘要, 朴素贝叶斯, 多维度特征

Abstract: Existing automatic summary generation methods for long texts cannot fully measure the similarity characteristics of sentences,which results in the decrease of the accuracy of summary generation.To address the problem,this paper proposes an automatic summary generation method based on graph integration model.The method calculates the word frequency,semantic features and syntactic features of text sentences,and then uses the naive Bayesian method to transform the fusion problem of multidimensional text features into a graph integration mode,which improves the calculation accuracy of similarity between sentences.On this basis,a text summary is generated by using TextRank algorithm.Experimental results show that compared with the traditional summary generation method based on the sequence-to-sequence model and summary extraction method based on multi-dimensional features of sentences,the proposed method achieves a higher ROUGE index.It can effectively synthesize the multidimensional features of sentences,and improves the accuracy of summary generation.

Key words: sentence similarity, graph integration model, text summarization, naive Bayes, multidimensional feature

中图分类号:

TP18

王青松, 张衡, 李菲. 基于文本多维度特征的自动摘要生成方法[J]. 计算机工程, 2020, 46(9): 110-116.

WANG Qingsong, ZHANG Heng, LI Fei. Automatic Summary Generation Method Based on Multidimensional Text Feature[J]. Computer Engineering, 2020, 46(9): 110-116.

http://www.ecice06.com/CN/Y2020/V46/I9/110

图/表 5

20200915135249

20200915135252

20200915135255

20200915135258

20200915135302

参考文献

[1] EL-REFAIY A M,ABAS A R,EL-HENAWY I M.Determining extractive summary for a single document base-don collaborative filtering frequency prediction and mean shift clustering[J].IAENG International Journalof Computer Science,2019,46(3):494-505.
[2] DARMAWAN R,WIJAYA A.Integration distance similarity with keyword algorithm for improving cohesion between sentences in text summarization[C]//Proceedings of IOP Conference on Series Materials Science and Engineering.Washington D.C.,USA:IEEE Press,2019:12-19.
[3] LYNN H M,CHOI C,KIM P.An improved method of automatic text summarization for Web contents using lexical chain with semantic-related terms[J].Soft Computing,2018,22(12):4013-4023.
[4] JOSEF S,KAREL J.Update summarization based on lat-ent semantic analysis[C]//Proceedings of Text,Speech & Dialogue International Conference.Pilsen,Czech Republic:[s.n.],2009:77-84.
[5] SHEN Huadong,PENG Dunlu.AM-BRNN:automatic text summarization extraction model based on deep learning[J].Journal of Chinese Computer Systems,2018,39(6):1184-1189.(in Chinese)沈华东,彭敦陆.AM-BRNN:一种基于深度学习的文本摘要自动抽取模型[J].小型微型计算机系统,2018,39(6):1184-1189.
[6] SONG Shengli,HUANG Haitao,RUAN Tongxiao.Abstractive text summarization using LSTM-CNN based deep learning[J].Multimedia Tools and Applications,2019,78(1):857-875.
[7] MIHALCEA R.Graph-based ranking algorithms for sentence extraction,applied to text summarization[C]//Proceedings of ACL'04.New York,USA:ACM Press,2004:20.
[8] WANG Zixuan,LE Xiaoqiu,HE Yuanbiao.Recognizing core topic sentences with improved TextRank algorithm based on WMD semantic similarity[J].Data Analysis and Knowledge Discovery,2017,1(4):1-8.(in Chinese)王子璇,乐小虬,何远标.基于WMD语义相似度的TextRank改进算法识别论文核心主题句研究[J].数据分析与知识发现,2017,1(4):1-8.
[9] LI Nan,TAO Hongcai.A novel news summary algorithm combining BM25 and text features[J].Journal of Chengdu University of Information Technology,2018,32(2):113-118.(in Chinese)李楠,陶宏才.一种新的融合BM25与文本特征的新闻摘要算法[J].成都信息工程大学学报,2018,32(2):113-118.
[10] TANG Yizhi.Conceptual option from HowNet and relational analysis[J].Natural Science Journal of Xiangtan University,2009,31(1):135-140.(in Chinese)唐一之.基于知网的领域概念抽取与关系分析研究[J].湘潭大学自然科学学报,2009,31(1):135-140.
[11] XIONG Jing,LIU Yuntong,YUAN Dong.Dependency syntactic tree supported sentence similarity computing[J].Information Technology Journal,2013,12(20):5685-5688.
[12] MERING C V,JENSEN L J,SNEL B,et al.STRING:Known and predicted protein-protein associations,integrated and transferred across organisms[J].Nucleic Acids Research,2004,33,433-437.
[13] MIHALCEA R,TARAU P.TextRank:bringing order into texts[C]//Proceedings of International Conference on Empirical Methods in Natural Language Processing.Barcelona,Spain:[s.n.].2004:404-411.
[14] BOWMAN S R,ANGELI G,POTTS C,et al.A large annotated corpus for learning natural language inference[EB/OL].[2015-04-21].https://arxiv.org/abs/1508.05326.
[15] LI Qiuming,ZHANG Weishan,ZHANG Peiying.Similarity calculation model based on multiple features of sentences[J].Software Guide,2016,15(9):4-6.(in Chinese)李秋明,张卫山,张培颖.基于句子多种特征的相似度计算模型[J].软件导刊,2016,15(9):4-6.
[16] HERMANN K M,KOCISKY T,GREFENSTETTE E,et al.Teaching machines to read and comprehend[C]//Proceedings of IEEE International Conference on Neural Information Processing Systems.Washington D.C.,USA:IEEE Press,2015:1693-1701.
[17] SEE A,LIU P J,MANNING C D.Get to the point:summarization with pointer-generator networks[C]//Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics.Washington D.C.,USA:IEEE Press,2017:1073-1083.
[18] LIN C Y,OCH F J.Looking for a few good metrics:ROUGE and its evaluation[C]//Proceedings of the 4th NTCIR Workshop on Research in Information Access Technologies Information Retrieval,Question Answering and Summarization.Tokyo,Japan:[s.n.],2004:125-136.
[19] RUSH A M,CHOPRA S,WESTON J.A neural attention model for abstractive sentence summarization[C]//Proceedings of EMNLP'15.New York,USA:ACM Press,2015:379-389.
[20] BARRERA A,VERMA R.Combining syntax and semantics for automatic extractive single-document summarization[C]//Proceedings of International Conference on Computational Linguistics and Intelligent Text Processing.Berlin Germany:Springer,2012:366-377.
[21] KHAN R,QIAN Y,NAEEM S.Extractive based text Summarization using K-means and TF-IDF[J].Information Engineering and Electronic Business,2019,3:33-44.

选择文件类型/文献管理软件名称

选择包含的内容