面向查询的观点摘要模型研究：以<bold>Debatepedia</bold>为数据源

doi:10.3772/j.issn.1000-0135.2020.04.004

情报学报

2020, Vol. 39

Issue (4): 374-386 DOI: 10.3772/j.issn.1000-0135.2020.04.004

情报分析方法与技术

本期目录 | 过刊浏览 | 高级检索

面向查询的观点摘要模型研究：以Debatepedia为数据源

余传明¹, 郑智梁^1,2, 朱星宇¹, 安璐³

1.中南财经政法大学信息与安全工程学院，武汉 430073
2.McKelvey School of Engineering, Washington University in St. Louis,St. Louis,Missouri 63130
3.武汉大学信息管理学院，武汉 430072

Query-oriented Opinion Summarization Model Using Debatepedia as Datasource

Yu Chuanming¹, Zheng Zhiliang^1,2, Zhu Xingyu¹, An Lu³

1.School of Information and Safety Engineering, Zhongnan University of Economics and Law, Wuhan 430073
2.McKelvey School of Engineering, Washington University in St. Louis , St. Louis, Missouri 63130
3.School of Information Management, Wuhan University, Wuhan 430072

摘要
图/表
参考文献
相关文章 (15)

全文: PDF (1580 KB) HTML (191 KB)
输出: BibTeX | EndNote (RIS)

摘要本文系统性地研究面向查询的观点摘要任务，旨在构建一种查询式观点摘要模型框架，探究不同的摘要方法对摘要效果的影响。通过综合考虑情感倾向与句子相似度，从待检文档中抽取出待摘要语句，再结合神经网络和词嵌入技术生成摘要，进而构建面向查询的观点摘要框架。从Debatepedia网站上爬取议题和论述内容构建观点摘要实验数据集，将本文方法应用到该数据集上，以检验不同模型的效果。实验结果表明，在该数据集上，仅使用基于抽取式的方法生成的观点摘要质量更高，取得了最高的平均ROUGE分数、深度语义相似度分数和情感分数，较生成式方法分别提高6.58%、1.79%和11.52%，而比组合式方法提高了8.33%、2.80%和13.86%；同时，本文提出的句子深度语义相似度和情感分数评估指标有助于更好地评估面向查询的观点摘要模型效果。研究结果对于提升面向查询的观点摘要效果，促进观点摘要模型在情报学领域的应用具有重要意义。

	服务

	把本文推荐给朋友
	加入我的书架
	加入引用管理器
	E-mail Alert
	RSS
	作者相关文章
	余传明
	郑智梁
	朱星宇
	安璐

关键词 ：观点摘要, 信息抽取, 话语生成, 情感分析, 深度学习

收稿日期: 2019-10-10

基金资助:国家自然科学基金面上项目“面向跨语言观点摘要的领域知识表示与融合模型研究”（71974202）；国家自然科学基金重大课题“国家安全大数据综合信息集成与分析方法”（71790612）”。

作者简介: 余传明，男，1978年生，博士，教授，主要研究方向为数据挖掘、信息检索和商务智能等，E-mail:yuchuanming2003@126.com

引用本文:

余传明, 郑智梁, 朱星宇, 安璐. 面向查询的观点摘要模型研究：以Debatepedia为数据源[J]. 情报学报, 2020, 39(4): 374-386.
Yu Chuanming, Zheng Zhiliang, Zhu Xingyu, An Lu. Query-oriented Opinion Summarization Model Using Debatepedia as Datasource. 情报学报, 2020, 39(4): 374-386.

链接本文:

https://qbxb.istic.ac.cn/CN/10.3772/j.issn.1000-0135.2020.04.004 或 https://qbxb.istic.ac.cn/CN/Y2020/V39/I4/374

1 LinC Y. ROUGE: A package for automatic evaluation of summaries[C]// Proceedings of the Association for Computational Linguistics Workshop on Text Summarization Branches Out. Stroudsburg: Association for Computational Linguistics, 2004: 74-81.
2 NóbregaF A A, AgostiniV, CamargoR T, et al. Alignment-based sentence position policy in a news corpus for multi-document summarization[C]// Proceedings of the International Conference on Computational Processing of the Portuguese Language. Cham: Springer, 2014, 8775: 286-291.
3 张晗, 赵玉虹. 基于语义图的医学多文档摘要提取模型构建[J]. 图书情报工作, 2017, 61(8): 112-119.
4 VermaJ P. Evaluation of unsupervised learning based extractive text summarization technique for large scale review and feedback data[J]. Indian Journal of Science and Technology, 2017, 10(17): 1-3.
5 GeraniS, CareniniG, NgR T. Modeling content and structure for abstractive review summarization[J]. Computer Speech & Language, 2019, 53: 302-331.
6 KhanA, SalimN, FarmanH, et al. Abstractive text summarization based on improved semantic graph approach[J]. International Journal of Parallel Programming, 2018, 46(5): 992-1016.
7 López CondoriR E, Salgueiro PardoT A. Opinion summarization methods: Comparing and extending extractive and abstractive approaches[J]. Expert Systems with Applications, 20172, 78: 124-134.
8 DingY, JiangJ. Towards opinion summarization from online forums[C]// Proceedings of the International Conference on Recent Advances in Natural Language Processing. Stroudsburg: Association for Computational Linguistics, 2015: 138-146.
9 MoreM, TidkeB. Social media online opinion summarization using ensemble technique[C]// Proceedings of the International Conference on Pervasive Computing. New York: IEEE, 2015: 1-6.
10 HuangS L, ChengW C. Discovering Chinese sentence patterns for feature-based opinion summarization[J]. Electronic Commerce Research and Applications, 2015, 14(6): 582-591.
11 OthmanR, BelkarouiR, FaizR. Customer opinion summarization based on Twitter conversations[C]// Proceedings of the 6th International Conference on Web Intelligence, Mining and Semantics. New York: ACM Press, 2016: 4.
12 WangD, LiuY. Opinion summarization on spontaneous conversations[J]. Computer Speech & Language, 2015, 34(1): 61-82.
13 温浩, 乔晓东. 文摘创新点的语义本体模型研究[J]. 情报学报, 2017, 36(9): 964-971.
14 沈思, 胡昊天, 叶文豪, 等. 基于全字语义的摘要结构功能自动识别研究[J]. 情报学报, 2019, 38(1): 79-88.
15 唐晓波, 肖璐. 基于单句粒度的微博主题挖掘研究[J]. 情报学报, 2014, 33(6): 623-632.
16 刘如, 张惠娜, 杜丽萍, 等. 基于情报3.0工作思路的自动简报系统设计与实现[J]. 情报学报, 2018, 37(2): 172-182.
17 刘柏嵩, 赵福青. 基于微观点的产品评论微摘要研究[J]. 情报学报, 2015, 34(9): 970-977.
18 MaJ, LuoS L, YaoJ G, et al. Efficient opinion summarization on comments with online-LDA[J]. International Journal of Computers Communications & Control, 2016, 11(3): 414-427.
19 RautV B, LondheD D. Opinion mining and summarization of hotel reviews [C]// Proceedings of the International Conference on Computational Intelligence and Communication Networks. New York: IEEE, 2014: 556-559.
20 KimH D, CastellanosM G, HsuM, et al. Ranking explanatory sentences for opinion summarization[C]// Proceedings of the 36th International ACM SIGIR Conference on Research and Development in Information Retrieval. New York: ACM Press, 2013: 1069-1072.
21 王树义, 廖桦涛, 吴查科. 基于情感分类的竞争企业新闻文本主题挖掘[J]. 数据分析与知识发现, 2018, 2(3): 70-78.
22 NallapatiR, XiangB, ZhouB. Sequence-to-sequence RNNs for text summarization[OL]. [2019-04-30]. https://openreview.net/pdf?id=gZ9OMgQWoIAPowrRUAN6.
23 NallapatiR, ZhouB, GulcehreC, et al. Abstractive text summarization using sequence-to-sequence RNNs and beyond[OL]. [2019-04-30]. https://arxiv.org/pdf/1602.06023.pdf%20http://arxiv.org/abs/1602.06023.pdf.
24 RossielloG, BasileP, SemeraroG, et al. Improving neural abstractive text summarization with prior knowledge[OL]. [2019-04-30]. https://arxiv.org/pdf/1812.02303.
25 苏放, 王晓宇, 张治. 基于注意力机制的评论摘要生成[J]. 北京邮电大学学报, 2018, 41(3): 7-13.
26 余传明, 朱星宇, 龚雨田, 等. 基于序列到序列模型的抽象式中文文本摘要研究[J]. 图书情报工作, 2019, 63(11): 108-117.
27 ZhangY, ErM J, ZhaoR, et al. Multiview convolutional neural networks for multidocument extractive summarization[J]. IEEE Transactions on Cybernetics, 2017, 47(10): 3230-3242.
28 LiQ D, JinZ P, WangC, et al. Mining opinion summarizations using convolutional neural networks in Chinese microblogging systems[J]. Knowledge-Based Systems, 2016, 107(6): 289-300.
29 WuH B, GuY W, SunS D, et al. Aspect-based opinion summarization with convolutional neural networks[C]// Proceedings of the International Joint Conference on Neural Networks. New York: IEEE, 2016: 3157-3163.
30 WangL, RaghavanH, CardieC, et al. Query-focused opinion summarization for user-generated content[OL]. [2019-04-30]. https://arxiv.org/pdf/1606.05702.pdf.
31 AbdiA, ShamsuddinS M, AliguliyevR M. QMOS: Query-based multi-documents opinion-oriented summarization[J]. Information Processing & Management, 2018, 54(2): 318-338.
32 BahdanauD, ChoK, BengioY. Neural machine translation by jointly learning to align and translate[OL]. [2019-04-30]. https://arxiv.org/pdf/1409.0473.pdf.
33 LuongM T, PhamH, ManningC D. Effective approaches to attention-based neural machine translation[OL]. [2019-04-30]. https://arxiv.org/pdf/1508.04025.pdf.
34 ErkanG, RadevD R. LexRank: Graph-based lexical centrality as salience in text summarization[J]. Journal of Artificial Intelligence Research, 2004, 22(1): 457-479.
35 AroraS, LiangY, MaT. A simple but tough-to-beat baseline for sentence embeddings[OL]. [2019-04-30]. https://openreview.net/pdf?id=SyK00v5xx.
36 KusnerM J, SunY, KolkinN I, et al. From word embeddings to document distances[OL]. [2019-04-30]. http://proceedings.mlr.press/v37/kusnerb15.pdf.
37 RobertsonS E, WalkerS. Some simple effective approximations to the 2-Poisson model for probabilistic weighted retrieval[C]// Proceedings of the Annual Conference of Special Interest Group on Information Retrieval. London: Springer, 1994: 232-241.