基于主次关系特征的自动文摘方法

doi:10.11896/JsJkx.191000007

摘要/Abstract

摘要： 自动文摘研究是指通过自然语言处理技术对原始文本进行压缩、提炼,在保留文档核心思想的同时为用户提供简明扼要的文字描述。传统的自动文摘方法通常只考虑字、词、句子等浅层的文本语义信息,而忽略了深层的主次关系等篇章结构信息对抽取文档核心句子的指导作用。对此,提出一种基于主次关系特征的自动文摘方法。该方法基于长短期记忆网络(Long Short-Term Memory,LSTM)神经网络构建了基于主次关系特征的单文档抽取式摘要模型,通过双向LSTM神经网络模型对句子信息和主次关系信息进行信息增强和语义编码,并利用单向LSTM神经网络对编码后的信息进行摘要抽取。实验结果表明,与当前主流的单文档抽取式摘要方法相比,该方法在摘要的准确性、稳定性和ROUGE评价指标上均有显著的提高。

关键词: LSTM, 抽取式摘要, 神经网络, 主次关系, 自然语言处理

Abstract: Automatic summarization technology refers to providing users with a concise text description by compressing and refining the original text while retaining the core idea of document.Usually,the traditional method only considers the shallow textual semantic information and neglects the guiding role of the structure information such as the primary and secondary relations in core sentences extraction.Therefore,this paper proposes an automatic summarization method based on the primary and secondary relation feature.This method utilizes the neural network to construct a single document extractive summarization model based on primary and secondary relation feature.The Bi-LSTM neural network model is used to encode the sentence information and primary and secondary relation information,and the LSTM neural network is utilized to summarize the encoded information.Experimental results show that the proposed method has a significant improvement in accuracy,stability and the ROUGE evaluation index compared with the current mainstream single document extractive summarization methods.

Key words: Extractive summarization, LSTM, Natural language processing, Neural network, Primary and secondary relation

中图分类号:

TP391

张迎, 张宜飞, 王中卿, 王红玲. 基于主次关系特征的自动文摘方法[J]. 计算机科学, 2020, 47(6A): 6-11. https://doi.org/10.11896/JsJkx.191000007

ZHANG Ying, ZHANG Yi-fei, WANG Zhong-qing and WANG Hong-ling. Automatic Summarization Method Based on Primary and Secondary Relation Feature[J]. Computer Science, 2020, 47(6A): 6-11. https://doi.org/10.11896/JsJkx.191000007

参考文献

[1] LUHN H P.The automatic creation of literature abstracts.IBM Journal of Research and Development,1958,2(2):159-165.
[2] CHU X M,ZHU Q M,ZHOU G D.Discourse Primary-Secondary Relationships in Natural Language Processing.Journal of Computer Science,2017,40(4):842-860.
[3] MIHALCEA R,TARAU P.TextRank:Bringing Order into Texts//Proc Conference on Empirical Methods in Natural Language Processing.2004:404-411.
[4] ERKAN G,RADEV D R.LexPageRank:Prestige in Multi-Do-cument Text Summariztion//Conference on Empirical Methodsin Natural Language Processing(EMNLP 2004).ACL,2004:365-371.
[5] KUPIEC J,PEDERSEN J,CHEN F.A trainable document sum-marizer//Proceedings of the 18th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval.ACM,1995:68-73.
[6] CONROY J M,SCHLESINGER J D,DIANNE P O,et al.Using {HMM} and Logistic Regression to Generate Extract Summaries for {DUC}.温泉科学,2001,63(329):66-75.
[7] KIM Y.Convolutional neural networks for sentence classification.arXiv:1408.5882,2014.
[8] LIU P,QIU X,HUANG X.Recurrent neural network for text classification with multi-task learning.arXiv:1605.05101,2016.
[9] ZHOU C,SUN C,LIU Z,et al.A C-LSTM neural network for text classification.arXiv:1511.08630,2015.
[10] CHOPRA S,AULI M,RUSH A M.Abstractive sentence summarization with attentive recurrent neural networks//Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics:Human Language Technologies.2016:93-98.
[11] RUSH A M,CHOPRA S,WESTON J.A neural attention model for abstractive sentence summarization.arXiv:1509.00685,2015.
[12] SEE A,LIU P J,MANNING C D.Get To The Point:Summarization with Pointer-Generator Net-works//Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics.2017:1073-1083.
[13] CARLSON,LYNN,MARCU,et al.Building a dis-course-tagged corpus in the framework of Rhetorical Structure Theory//Current and New Directions in Discourse and Dialogue.Netherlands:Springer,2003:2655-2661.
[14] ZHOU Y,XUE N.The Chinese Discourse TreeBank:A Chinese corpus annotated with discourse relations.Language Resources and Evaluation,2015,49(2):397-431.
[15] HERNAULT H,PRENDINGER H,ISHIZUKA M.HILDA:A discourse parser using support vector machine classification.Dialogue & Discourse,2010,1(3).
[16] FENG V W,HIRST G.Text-level discourse parsing with rich linguistic features//Proceedings of the 50th Annual Meeting of the Association for Computational Linguistics.2012:60-68.
[17] CHU X,WANG Z,ZHU Q,et al.Recognizing nuclearity between Chinese Discourse units//2015 International Conferenceon Asian Language Processing (IALP).IEEE,2015:197-200.
[18] SUN J,LI Y C,ZHOU G D,et al.Research of Chinese Implicit Discourse Relation Recognition.Journal of Peking University (Natural Science Edition),2014,50(1):111-117.
[19] SUN C,KONG F.A Transition-based Framework for Chinese Discourse Structure Parsing.Journal of Chinese Information Processing,2018,32(12):48-56.
[20] LI Y C.Research of Chinese Discourse Stucture Representation and Resource Construction.Suzhou:Soochow University of Defense Technology,2015.
[21] LIN C Y,HOVY E.Automatic Evaluation of Summaries Using n-gram Co-occurrence Statistics//Conference of the North American Chapter of the Association for Computational Linguistics on Human Language Technology.Association for Computational Linguistics,2003.
[22] HUA L,WAN X,LI L.Overview of the NLPCC 2017 Shared Task:Single Document Summarization//National CCF Conference on Natural Language Processing and Chinese Computing.Cham:Springer,2017:942-947.
[23] WAN X,YANG J.Multi-document summarization using cluster-based link analysis//Proceedings of the 31st annual international ACM SIGIR Conference on Research and Development in Information Retrieval.ACM,2008:299-306.
[24] KIM Y.Convolutional neural networks for sentence classification.arXiv:1408.5882,2014.

相关文章 15

[1]	宁晗阳, 马苗, 杨波, 刘士昌. 密码学智能化研究进展与分析 Research Progress and Analysis on Intelligent Cryptology 计算机科学, 2022, 49(9): 288-296. https://doi.org/10.11896/jsjkx.220300053
[2]	周芳泉, 成卫青. 基于全局增强图神经网络的序列推荐 Sequence Recommendation Based on Global Enhanced Graph Neural Network 计算机科学, 2022, 49(9): 55-63. https://doi.org/10.11896/jsjkx.210700085
[3]	周乐员, 张剑华, 袁甜甜, 陈胜勇. 多层注意力机制融合的序列到序列中国连续手语识别和翻译 Sequence-to-Sequence Chinese Continuous Sign Language Recognition and Translation with Multi- layer Attention Mechanism Fusion 计算机科学, 2022, 49(9): 155-161. https://doi.org/10.11896/jsjkx.210800026
[4]	李宗民, 张玉鹏, 刘玉杰, 李华. 基于可变形图卷积的点云表征学习 Deformable Graph Convolutional Networks Based Point Cloud Representation Learning 计算机科学, 2022, 49(8): 273-278. https://doi.org/10.11896/jsjkx.210900023
[5]	郝志荣, 陈龙, 黄嘉成. 面向文本分类的类别区分式通用对抗攻击方法 Class Discriminative Universal Adversarial Attack for Text Classification 计算机科学, 2022, 49(8): 323-329. https://doi.org/10.11896/jsjkx.220200077
[6]	王润安, 邹兆年. 基于物理操作级模型的查询执行时间预测方法 Query Performance Prediction Based on Physical Operation-level Models 计算机科学, 2022, 49(8): 49-55. https://doi.org/10.11896/jsjkx.210700074
[7]	陈泳全, 姜瑛. 基于卷积神经网络的APP用户行为分析方法 Analysis Method of APP User Behavior Based on Convolutional Neural Network 计算机科学, 2022, 49(8): 78-85. https://doi.org/10.11896/jsjkx.210700121
[8]	朱承璋, 黄嘉儿, 肖亚龙, 王晗, 邹北骥. 基于注意力机制的医学影像深度哈希检索算法 Deep Hash Retrieval Algorithm for Medical Images Based on Attention Mechanism 计算机科学, 2022, 49(8): 113-119. https://doi.org/10.11896/jsjkx.210700153
[9]	檀莹莹, 王俊丽, 张超波. 基于图卷积神经网络的文本分类方法研究综述 Review of Text Classification Methods Based on Graph Convolutional Network 计算机科学, 2022, 49(8): 205-216. https://doi.org/10.11896/jsjkx.210800064
[10]	闫佳丹, 贾彩燕. 基于双图神经网络信息融合的文本分类方法 Text Classification Method Based on Information Fusion of Dual-graph Neural Network 计算机科学, 2022, 49(8): 230-236. https://doi.org/10.11896/jsjkx.210600042
[11]	齐秀秀, 王佳昊, 李文雄, 周帆. 基于概率元学习的矩阵补全预测融合算法 Fusion Algorithm for Matrix Completion Prediction Based on Probabilistic Meta-learning 计算机科学, 2022, 49(7): 18-24. https://doi.org/10.11896/jsjkx.210600126
[12]	张源, 康乐, 宫朝辉, 张志鸿. 基于Bi-LSTM的期货市场关联交易行为检测方法 Related Transaction Behavior Detection in Futures Market Based on Bi-LSTM 计算机科学, 2022, 49(7): 31-39. https://doi.org/10.11896/jsjkx.210400304
[13]	杨炳新, 郭艳蓉, 郝世杰, 洪日昌. 基于数据增广和模型集成策略的图神经网络在抑郁症识别上的应用 Application of Graph Neural Network Based on Data Augmentation and Model Ensemble in Depression Recognition 计算机科学, 2022, 49(7): 57-63. https://doi.org/10.11896/jsjkx.210800070
[14]	张颖涛, 张杰, 张睿, 张文强. 全局信息引导的真实图像风格迁移 Photorealistic Style Transfer Guided by Global Information 计算机科学, 2022, 49(7): 100-105. https://doi.org/10.11896/jsjkx.210600036
[15]	戴朝霞, 李锦欣, 张向东, 徐旭, 梅林, 张亮. 基于DNGAN的磁共振图像超分辨率重建算法 Super-resolution Reconstruction of MRI Based on DNGAN 计算机科学, 2022, 49(7): 113-119. https://doi.org/10.11896/jsjkx.210600105

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed