Survey of extractive text summarization based on unsupervised learning and supervised learning

doi:10.11772/j.issn.1001-9081.2023040537

Journal of Computer Applications ›› 2024, Vol. 44 ›› Issue (4): 1035-1048.DOI: 10.11772/j.issn.1001-9081.2023040537

• Artificial intelligence • Previous Articles Next Articles

Survey of extractive text summarization based on unsupervised learning and supervised learning

Xiawuji¹^,², Heming HUANG¹^,²(), Gengzangcuomao¹^,², Yutao FAN¹^,²

^1.College of Computer，Qinghai Normal University，Xining Qinghai 810008，China
^2.State Key Laboratory of Tibetan Intelligent Information Processing and Application （Qinghai Normal University），Xining Qinghai 810008，China

Received:2023-05-06 Revised:2023-07-19 Accepted:2023-07-25 Online:2023-12-04 Published:2024-04-10
Contact: Heming HUANG
About author:Xiawuji， born in 1982， Ph. D. candidate， associate professor. Her research interests include pattern recognition and intelligent systems， Tibetan intelligent information processing.
HUANG Heming， born in 1969， Ph. D.， professor. His research interests include pattern recognition and artificial intelligence.
Gengzangcuomao， born in 1993， Ph. D. candidate. Her research interests include pattern recognition and intelligent systems.
FAN Yutao， born in 1977， Ph. D. candidate， associate professor. Her research interests include pattern recognition and intelligent systems.
Supported by:
National Natural Science Foundation of China(62066039);Qinghai Provincial Natural Science Foundation(2022-ZJ-925);Independent Project of State Key Laboratory of Tibetan Intelligent Information Processing and Application(2022-SKL-007)

基于无监督学习和监督学习的抽取式文本摘要综述

夏吾吉¹^,², 黄鹤鸣¹^,²(), 更藏措毛¹^,², 范玉涛¹^,²

^1.青海师范大学计算机学院，西宁 810008
^2.藏语智能信息处理及应用国家重点实验室（青海师范大学），西宁 810008

通讯作者: 黄鹤鸣
作者简介:夏吾吉（1982—），女（藏族），青海尖扎人，副教授，博士研究生，CCF会员，主要研究方向：模式识别与智能系统、藏语智能信息处理
黄鹤鸣（1969—），男（藏族），青海乐都人，教授，博士生导师，博士，CCF会员，主要研究方向：模式识别与人工智能 huanghm@qhnu.edu.cn
更藏措毛（1993—），女（藏族），青海共和人，博士研究生，主要研究方向：模式识别与智能系统
范玉涛（1977—），女，山西大同人，副教授，博士研究生，主要研究方向：模式识别与智能系统。
基金资助:
国家自然科学基金资助项目(62066039);青海省自然科学基金资助项目(2022?ZJ?925);藏语智能信息处理及应用国家重点实验室自主项目(2022?SKL?007)

Abstract

Abstract:

Different from generative summarization methods， extractive summarization methods are more feasible to implement， more readable， and more widely used. At present， the literatures on extractive summarization methods mostly analyze and review some specific methods or fields， and there is no multi-faceted and multi-lingual systematic review. Therefore， the meanings of text summarization generation were discussed， related literatures were systematically reviewed， and the methods of extractive text summarization based on unsupervised learning and supervised learning were analyzed multi-dimensionally and comprehensively. First， the development of text summarization techniques was reviewed， and different methods of extractive text summarization were analyzed， including the methods based on rules， Term Frequency-Inverse Document Frequency （TF-IDF）， centrality， potential semantic， deep learning， graph sorting， feature engineering， and pre-training learning， etc. Also， comparisons of advantages and disadvantages among different algorithms were made. Secondly， datasets in different languages for text summarization and popular evaluation metrics were introduced in detail. Finally， problems and challenges for research of extractive text summarization were discussed， and solutions and research trends were presented.

Key words: extractive summarization, unsupervised learning, supervised learning, dataset, evaluation metric

摘要：

相较于生成式摘要方法，抽取式摘要方法简单易行、可读性强，使用范围广。目前，抽取式摘要方法综述文献仅对特定的某个方法或领域进行分析综述，缺乏多方面、多语种的系统性综述，因此探讨文本摘要生成任务的内涵，通过系统梳理和提炼现有的相关文献，对无监督学习和监督学习的抽取式文本摘要技术进行多维度、全方位的分析。首先，回顾文本摘要技术的发展，分析不同的抽取式文本摘要方法，主要包括基于规则、词频-逆文件概率（TF-IDF）、中心性方法、潜在语义、深度学习、图排序、特征工程和预训练学习等，并对比不同方法的差异；其次，详细介绍不同语种文本摘要生成的常用数据集和主流的评价指标，通过不同的实验指标对相同数据集上的方法进行比较；最后，指出当前抽取式文本摘要研究中存在的主要问题和挑战，并提出具体的解决思路和未来发展趋势。

关键词: 抽取式摘要, 无监督学习, 监督学习, 数据集, 评价指标

CLC Number:

TP391.1

Xiawuji, Heming HUANG, Gengzangcuomao, Yutao FAN. Survey of extractive text summarization based on unsupervised learning and supervised learning[J]. Journal of Computer Applications, 2024, 44(4): 1035-1048.

夏吾吉, 黄鹤鸣, 更藏措毛, 范玉涛. 基于无监督学习和监督学习的抽取式文本摘要综述[J]. 《计算机应用》唯一官方网站, 2024, 44(4): 1035-1048.

Figures/Tables 9

References 83

1	GAMBHIR M， GUPTA V. Recent automatic text summarization techniques： a survey ［J］. Artificial Intelligence Review， 2017， 47（1）： 1-66. 10.1007/s10462-016-9475-9
2	ABDELALEEM N M， KADER H M A， SALEM R. A brief survey on text summarization techniques ［J］. International Journal of Electronics and Information Engineering， 2019， 10（2）： 76-89.
3	侯圣峦，张书涵，费超群.文本摘要常用数据集和方法研究综述［J］.中文信息学报，2019，33（5）：1-16. 10.3969/j.issn.1003-0077.2019.05.001
	HOU S L， ZHANG S H， FEI C Q. A survey to text summarization： popular datasets and methods ［J］. Journal of Chinese Information Processing， 2019，33（5）：1-16. 10.3969/j.issn.1003-0077.2019.05.001
4	LUHN H P. The automatic creation of literature abstracts ［J］. IBM Journal of Research and Development， 1958， 2（2）： 159-165. 10.1147/rd.22.0159
5	EDMUNDSON H P. New methods in automatic extracting ［J］. Journal of the ACM， 1969， 16（2）： 264-285. 10.1145/321510.321519
6	MILLER G A. WordNet： a lexical database for English ［J］. Communications of the ACM， 1995， 38（11）： 39-41. 10.1145/219717.219748
7	HOU S， HUANG Y， FEI C， et al. Holographic lexical chain and its application in Chinese text summarization ［C］// Proceedings of the 1st Asia-Pacific Web and Web-Age Information Management Joint International Conference on Web and Big Data. Cham： Springer， 2017： 266-281. 10.1007/978-3-319-63579-8_21
8	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. 10.1007/s00500-017-2612-9
9	GARCÍA-HERNÁNDEZ R A， LEDENEVA Y. Word sequence models for single text summarization ［C］// Proceedings of the 2009 2nd International Conferences on Advances in Computer-Human Interactions. Washington， DC： IEEE Computer Society， 2009： 44-48. 10.1109/achi.2009.58
10	SARKAR K. An approach to summarizing Bengali news documents ［C］// Proceedings of the 2012 International Conference on Advances in Computing， Communications and Informatics. New York： ACM， 2012： 857-862. 10.1145/2345396.2345535
11	EL-BELTAGY S R， REFEA A. KP-Miner： participation in SemeVal-2 ［C］// Proceedings of the 5th International Workshop on Semantic Evaluation. Stroudsburg： ACL， 2010： 190-193.
12	VANDERWENDE L， SUZUKI H， BROCKETT C， et al. Beyond SumBasic： task-focused summarization with sentence simplification and lexical expansion ［J］. Information Processing & Management， 2007， 43（6）： 1606-1618. 10.1016/j.ipm.2007.01.023
13	MANI I， BLOEDORN E. Multi-document summarization by graph search and matching ［C］// Proceedings of the 14th National Conference on Artificial Intelligence and 9th Conference on Innovative Applications of Artificial Intelligence Conference. Palo Alto： AAAI Press， 1997： 622-628.
14	RADEV D R， JING H， STYŚ M， et al. Centroid-based summarization of multiple documents ［J］. Information Processing & Management， 2004， 40（6）： 919-938. 10.1016/j.ipm.2003.10.006
15	WAN X， YANG J. Multi-document summarization using cluster-based link analysis ［C］// Proceedings of the 31st Annual International ACM SIGIR Conference on Research and Development in Information Retrieval. New York： ACM， 2008： 299-306. 10.1145/1390334.1390386
16	WAN X. Using bilingual information for cross-language document summarization ［C］// Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics： Human Language Technologies. Stroudsburg： ACL， 2011： 1546-1555.
17	ZHANG Y， CHU C-H， JI X， et al. Correlating summarization of multi-source news with k-way graph bi-clustering ［J］. ACM SIGKDD Explorations Newsletter， 2004， 6（2）： 34-42. 10.1145/1046456.1046461
18	WAN X， XIAO J. Graph-based multi-modality learning for topic-focused multi-document summarization ［C］// Proceedings of the 21st International Joint Conference on Artificial Intelligence. San Francisco： Morgan Kaufmann Publishers Inc， 2009： 1586-1591. 10.1145/1645953.1646184
19	GONG Y， LIU X. Generic text summarization using relevance measure and latent semantic analysis ［C］// Proceedings of the 24th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval. New York： ACM， 2001： 19-25. 10.1145/383952.383955
20	MURRAY G， RENALS S， CARLETTA J. Extractive summarization of meeting recordings ［C］// Proceedings of the 9th European Conference on Speech Communication and Technology. ［S.l.］： International Speech Communication Association， 2005： 593-596. 10.21437/interspeech.2005-59
21	STEINBERGER J， KABADJOV M A， POESIO M， et al. Improving LSA-based summarization with anaphora resolution ［C］// Proceedings of the 2005 Conference on Human Language Technology and Empirical Methods in Natural Language Processing. Stroudsburg： ACL， 2005： 1-8. 10.3115/1220575.1220576
22	GEETHA J K， DEEPAMALA N. Kannada text summarization using latent semantic analysis ［C］// Proceedings of the 2015 International Conference on Advances in Computing， Communications and Informatics. Piscataway： IEEE， 2015： 1508-1512. 10.1109/icacci.2015.7275826
23	LIU Y， ZHONG S-H， LI W J. Query-oriented multi-document summarization via unsupervised deep learning ［C］// Proceedings of the 26th AAAI Conference on Artificial Intelligence. Palo Alto： AAAI Press， 2012： 1699-1705.
24	HE Z， CHEN C， BU J， et al. Document summarization based on data reconstruction ［C］// Proceedings of the 26th AAAI Conference on Artificial Intelligence. Palo Alto： AAAI Press， 2012： 620-626.
25	KOBAYASHI H， NOGUCHI M， YATSUKA T. Summarization based on embedding distributions ［C］// Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing. Stroudsburg： ACL， 2015： 1984-1989. 10.18653/v1/d15-1232
26	王佳松.基于深度学习的多文档自动文摘研究［D］.长春：吉林大学，2017：25-29.
	WANG J S. Research on automatic multi-document summarization based on deep learning ［D］. Changchun： Jilin University， 2017： 25-29.
27	SONG H， REN Z， LIANG S， et al. Summarizing answer in non-factoid community question-answering ［C］// Proceeding of the 10th ACM International Conference on Web Search and Data Mining. New York： ACM， 2017： 405-414. 10.1145/3018661.3018704
28	LI P， WANG Z， LAM W， et al. Salience Estimation via variational auto-encoders for multi-document summarization ［C］// Proceedings of the 31st AAAI Conference on Artificial Intelligence. Palo Alto： AAAI Press， 2017： 3497-3503. 10.1609/aaai.v31i1.11007
29	REN Z， SONG H， LI P， et al. Using sparse coding for answer summarization in non-factoid community question-answering ［C/OL］// Proceedings of the 2nd WebQA Workshop. Waterloo： University of Waterloo ［2023-04-01］. . 10.1145/3018661.3018704
30	HAVELIWALA T H. Topic-sensitive PageRank： a context-sensitive ranking algorithm for Web search ［J］. IEEE Transactions on Knowledge and Data Engineering， 2003， 15（4）： 784-796． 10.1109/tkde.2003.1208999
31	BADRINATH R， VENKATASUBRAMANIYAN S， MADHAVAN C E V. Improving query focused summarization using look-ahead strategy ［C］// Proceedings of the 33rd European Conference on Advances in Information Retrieval. Berlin： Springer， 2011： 641-652. 10.1007/978-3-642-20161-5_64
32	WEI F， LI W， LU Q， et al. A document-sensitive graph model for multi-document summarization ［J］. Knowledge and Information Systems， 2010， 22（2）： 245-259. 10.1007/s10115-009-0194-2
33	李伟，闫晓东，解晓庆.基于改进 TextRank 的藏文抽取式摘要［J］.中文信息学报，2020，34（9）：36-43.
	LI W， YAN X D， XIE X Q. An improved TextRank for Tibetan summarization ［J］. Journal of Chinese Information Processing， 2020， 34（9）： 36-43.
34	GARG N， FAVRE B， RIEDHAMMER K， et al. ClusterRank： a graph based method for meeting summarization ［C］// Proceedings of the 10th Annual Conference of the International Speech Communication Association. ［S.l.］： International Speech Communication Association， 2009： 1499-1502. 10.21437/interspeech.2009-456
35	PARVEEN D， STRUBE M. Integrating importance， non-redundancy and coherence in graph-based extractive summarization ［C］// Proceedings of the 24th International Joint Conference on Artificial Intelligence. Palo Alto： AAAI Press， 2015： 1298-1304. 10.18653/v1/d15-1226
36	THU H N T， NGOC D V T. Improve Bayesian network to generating Vietnamese sentence reduction ［J］. IERI Procedia， 2014， 10： 190-195. 10.1016/j.ieri.2014.09.076
37	CONROY J M， O’LEARY D P. Text summarization via hidden Markov models ［C］// Proceedings of the 24th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval. New York： ACM， 2001： 406-407. 10.1145/383952.384042
38	GILLICK D， FAVRE B. A scalable global model for summarization ［C］// Proceedings of the 2009 NAACL HLT Workshop on Integer Linear Programming for Natural Language Processing. Stroudsburg： ACL， 2009： 10-18. 10.3115/1611638.1611640
39	WAN X， CAO Z， WEI F， et al. Multi-document summarization via discriminative summary reranking ［EB/OL］. （2015-07-08）［2023-04-01］. .
40	SHEN D， SUN J-T， LI H， et al. Document summarization using conditional random fields ［C］// Proceedings of the 20th International Joint Conference on Artificial Intelligence. San Francisco： Morgan Kaufmann Publishers Inc.， 2007： 2862-2867.
41	ITTI L， BALDI P. Bayesian surprise attracts human attention ［J］. Vision Research， 2009， 49（10）： 1295-1306. 10.1016/j.visres.2008.09.007
42	LOUIS A. A Bayesian method to incorporate background knowledge during automatic text summarization ［C］// Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics. Stroudsburg： ACL， 2014： 333-338. 10.3115/v1/p14-2055
43	ABDI A， SHAMSUDDIN S M， HASAN S， et al. Machine learning-based multi-documents sentiment-oriented summarization using linguistic treatment ［J］. Expert Systems with Application， 2018， 109： 66-85. 10.1016/j.eswa.2018.05.010
44	SHEN Y， HE X， GAO J， et al. Learning semantic representations using convolutional neural networks for web search ［C］// Proceedings of the 23rd International Conference on World Wide Web. New York： ACM， 2014： 373-374. 10.1145/2567948.2577348
45	YIN W， PEI Y. Optimizing sentence modeling and selection for document summarization ［C］// Proceedings of the 24th International Joint Conference on Artificial Intelligence. Palo Alto： AAAI Press， 2015： 1383-1389.
46	CAO Z， WEI F， LI S， et al. Learning summary prior representation for extractive summarization ［C］// Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing （Volume 2： Short Papers）. Stroudsburg： ACL， 2015： 829-833. 10.3115/v1/p15-2136
47	CAO Z， LI W， LI S， et al. AttSum： joint learning of focusing and summarization with neural attention ［C］// Proceedings of the 26th International Conference on Computational Linguistics： Technical Papers. Stroudsburg： ACL， 2016： 547-556. 10.3115/v1/p15-2136
48	CAO Z， LI W， LI S， et al. Improving multi-document summarization via text classification ［C］// Proceedings of the 31st AAAI Conference on Artificial Intelligence. Palo Alto： AAAI Press， 2017： 3053-3059. 10.1609/aaai.v31i1.10955
49	ZHANG Y， ER M J， ZHAO R， et al. Multiview convolutional neural networks for multi-document extractive summarization ［J］. IEEE Transactions on Cybernetics， 2017， 47（10）： 3230-3242. 10.1109/tcyb.2016.2628402
50	NALLAPATI R， ZHAI F， ZHOU B. SummaRuNNer： a recurrent neural network based sequence model for extractive summarization of documents ［C］// Proceedings of the 31st AAAI Conference on Artificial Intelligence. Palo Alto： AAAI Press， 2017： 3075-3081. 10.1609/aaai.v31i1.10958
51	FILIPPOVA K， ALFONSECA E， COLMENARES C A， et al. Sentence compression by deletion with LSTMs ［C］// Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing. Stroudsburg： ACL， 2015： 360-368. 10.18653/v1/d15-1042
52	REN P， CHEN Z， REN Z， et al. Leveraging contextual sentence relations for extractive summarization using a neural attention model ［C］// Proceedings of the 40th International ACM SIGIR Conference on Research and Development in Information Retrieval. New York： ACM， 2017： 95-104. 10.1145/3077136.3080792
53	CHENG J， LAPATA M. Neural summarization by extracting sentences and words ［C］// Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics. Stroudsburg： ACL， 2016： 484-494. 10.18653/v1/p16-1046
54	SINGH A K， GUPTA M， VARMA V. Unity in diversity： learning distributed heterogeneous sentence representation for extractive summarization ［C］// Proceedings of the 2018 AAAI Conference on Artificial Intelligence. Palo Alto： AAAI Press， 2018： 5473-5480. 10.1609/aaai.v32i1.11994
55	WANG D， LIU P， ZHENG Y， et al. Heterogeneous graph neural networks for extractive document summarization ［C］// Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics. Stroudsburg： ACL， 2020： 6209-6219. 10.18653/v1/2020.acl-main.553
56	LIU Y. Fine-tune BERT for extractive summarization ［EB/OL］. （2019-09-05）［2023-04-01］. .
57	XU J， GAN Z， CHENG Y， et al. Discourse-aware neural extractive text summarization ［C］// Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics. Stroudsburg： ACL， 2020： 5021-5031. 10.18653/v1/2020.acl-main.451
58	LIU Y， LAPATA M. Text summarization with pre-trained Encoders ［C］// Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing. Stroudsburg： ACL， 2019： 3730-3740. 10.18653/v1/d19-1387
59	BELTAGY I， LO K， COHAN A. SciBERT： a pretrained language model for scientific text ［C］// Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing. Stroudsburg： ACL， 2019： 3615-3620. 10.18653/v1/d19-1371
60	LEWIS M， LIU Y H， GOYAL N，et al. BART： denoising sequence-to-sequence pre-training for natural language generation，translation，and comprehension ［C］// Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics. Stroudsburg： ACL， 2020： 7871-7880. 10.18653/v1/2020.acl-main.703
61	BELTAGY I， PETERS M E， COHAN A. Longformer： the long-document transformer ［EB/OL］. （2020-12-02）［2023-04-01］. .
62	ZHANG J， ZHAO Y， SALAH M， et al. PEGASUS： pre-training with extracted gap-sentences for abstractive summarization ［EB/OL］. （2020-07-10）［2023-04-01］. .
63	RUAN Q， OSTENDORFF M， REHM G. HiStruct+： improving extractive text summarization with hierarchical structure information ［C］// Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics. Stroudsburg： ACL， 2022： 1292-1308. 10.18653/v1/2022.findings-acl.102
64	PUGOY R A， H-Y KAO. Unsupervised extractive summarization-based representations for accurate and explainable collaborative filtering ［C］// Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing. Stroudsburg： ACL， 2021： 2981-2990. 10.18653/v1/2021.acl-long.232
65	XIAO W， BELTAGY I， CARENINI G， et al. PRIMERA： pyramid-based masked sentence pre-training for multi-document summarization ［C］// Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics. Stroudsburg： ACL， 2022： 5245-5263. 10.18653/v1/2022.acl-long.360
66	MORO G， RAGAZZI L， VALGIMIGLI L， et al. Discriminative marginalized probabilistic neural method for multi-document summarization of medical literature ［C］// Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics. Stroudsburg： ACL， 2022： 180-189. 10.18653/v1/2022.acl-long.15
67	ZHAO C， HUANG T， CHOWDHURY S B R， et al. Read top news first： a document reordering approach for multi-document news summarization ［C］// Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics. Stroudsburg： ACL， 2022： 613-621. 10.18653/v1/2022.findings-acl.51
68	ZHANG Z， ELFARDY H， DREYER M. Enhancing multi-document summarization with cross-document graph-based information extraction ［C］// Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics. Stroudsburg： ACL， 2023： 1696-1707. 10.18653/v1/2023.eacl-main.124
69	GRAFF D， CIERI C. English gigaword — linguistic data consortium ［EB/OL］. （2003-01-28）［2023-04-01］. .
70	HU B， CHEN Q， ZHU F. LCSTS： a large scale Chinese short text summarization dataset ［C］// Proceeding of the 2015 Conference on Empirical Methods in Natural Language Processing. Stroudsburg： ACL， 2015： 1967-1972. 10.18653/v1/d15-1229
71	NALLAPATI R， ZHOU B， DOS SANTOS C， et al. Abstractive text summarization using seq-to-seq RNNs and beyond ［C］// Proceedings of the 20th SIGNLL Conference on Computational Natural Language Learning. Stroudsburg： ACL， 2016： 280-290. 10.18653/v1/k16-1028
72	DURRETT G， BERG-KIRKPATRICK T， KLEIN D. Learning-based single-document summarization with compression and anaphoricity constraints ［C］// Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics （Volume 1： Long Papers）. Stroudsburg： ACL， 2016： 1998-2008. 10.18653/v1/p16-1188
73	GRUSKY M， NAAMAN M， ARTZI Y. Newsroom： a dataset of 1.3 million summaries with diverse extractive strategies ［C］// Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics： Human Language Technologies. Stroudsburg： ACL， 2018： 708-719. 10.18653/v1/n18-1065
74	KAMEZAWA H， NISHIDA N， SHIMIZU N， et al. RNSum： a large-scale dataset for automatic release note generation via commit logs summarization ［C］// Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics. Stroudsburg： ACL， 2022： 8718-8728. 10.18653/v1/2022.acl-long.597
75	ZHONG M， YIN D， YU T， et al. QMSum： a new benchmark for query-based multi-domain meeting summarization ［C］// Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics. Stroudsburg： ACL， 2021： 5905-5921. 10.18653/v1/2021.naacl-main.472
76	ZHANG Y， NI A， MAO Z， et al. SUMM ^N ： a multi-stage summarization framework for long input dialogues and documents ［C］// Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics （Volume 1： Long Papers）. Stroudsburg： ACL， 2022： 1592-1604. 10.18653/v1/2022.acl-long.112
77	FABBRI A， LI I， SHE T， et al. Multi-News： a large-scale multi-document summarization dataset and abstractive hierarchical model ［C］// Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics. Stroudsburg： ACL， 2019： 1074-1084. 10.18653/v1/p19-1102
78	NARAYAN S， COHEN S B， LAPATA M. Don’t give me the details， just the summary！ Topic-aware convolutional neural networks for extreme summarization ［C］// Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing. Stroudsburg： ACL， 2018： 1797-1807. 10.18653/v1/d18-1206
79	闫晓东，王羿钦，黄硕，等.藏文多文本摘要数据集［J］. 中国科学数据（中英文网络版），2022， 7（2）： 39-45. 10.11922/11-6035.csd.2021.0098.zh
	YAN X D， WANG Y Q， HUANG S， et al. A dataset of Tibetan text summarization ［J］. China Scientific Data， 2022， 7（2）： 39-45. 10.11922/11-6035.csd.2021.0098.zh
80	GAO Y， ZHAO W， EGER S. SUPERT： towards new frontiers in unsupervised evaluation metrics for multi-document summarization ［C］// Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics. Stroudsburg： ACL， 2020： 1347-1354. 10.18653/v1/2020.acl-main.124
81	NENKOVA A， PASSONNEAU R. Evaluating content selection in summarization： the pyramid method ［C］// Proceedings of the 2004 Human Language Technology Conference of the North American Chapter of the Association for Computational Linguistics. Stroudsburg： ACL， 2004： 145-152.
82	PAPINENI K， ROUKOS S， WARD T， et al. BLEU： a method for automatic evaluation of machine translation ［C］// Proceedings of the 40th Annual Meeting of the Association for Computational Linguistics. Stroudsburg： ACL， 2002： 311-318. 10.3115/1073083.1073135
83	LIN C-Y. ROUGE： a package for automatic evaluation of summaries ［C］// Proceedings of the 2004 Workshop on Text Summarization Branches Out. Stroudsburg： ACL， 2004： 74-81.

基础	模型	DUC‑2001			DUC‑2002			DUC‑2004
基础	模型	ROUGE_1	ROUGE_2	ROUGE_L	ROUGE_1	ROUGE_2	ROUGE_L	ROUGE_1	ROUGE_2	ROUGE_L
CNN	DivSelect+CNNLM^［45］	—	—	—	51.01	26.97	29.43	40.91	10.72	14.97
	PriorSum^［46］	35.98	7.89	—	36.63	8.97	—	38.91	10.07	—
	TCSum^［48］	36.45	7.66	—	36.90	8.61	—	38.27	9.66	—
	MV-CNN^［49］	35.99	7.91	—	36.71	9.02	—	39.07	10.06	—
CNN+RNN	CRSum+SF^［52］	36.54	8.75	—	38.90	10.28	—	39.53	10.60	—
Transformer	PRIMERA^［65］	—	—	—	—	—	—	35.10	7.20	17.90
Transformer	PRESUM+DR_sup^［67］	—	—	—	—	—	—	34.62	8.22	30.54

基础	模型	DUC‑2001			DUC‑2002			DUC‑2004
基础	模型	ROUGE_1	ROUGE_2	ROUGE_L	ROUGE_1	ROUGE_2	ROUGE_L	ROUGE_1	ROUGE_2	ROUGE_L
CNN	DivSelect+CNNLM^［45］	—	—	—	51.01	26.97	29.43	40.91	10.72	14.97
	PriorSum^［46］	35.98	7.89	—	36.63	8.97	—	38.91	10.07	—
	TCSum^［48］	36.45	7.66	—	36.90	8.61	—	38.27	9.66	—
	MV-CNN^［49］	35.99	7.91	—	36.71	9.02	—	39.07	10.06	—
CNN+RNN	CRSum+SF^［52］	36.54	8.75	—	38.90	10.28	—	39.53	10.60	—
Transformer	PRIMERA^［65］	—	—	—	—	—	—	35.10	7.20	17.90
Transformer	PRESUM+DR_sup^［67］	—	—	—	—	—	—	34.62	8.22	30.54

模型	CNN/DM			Multi‑News			Xsum
模型	ROUGE_1	ROUGE_2	ROUGE_L	ROUGE_1	ROUGE_2	ROUGE_L	ROUGE_1	ROUGE_2	ROUGE_L
PEGASUS^［62］	44.17	21.47	41.11	—	—	—	47.21	24.56	39.25
SummaRuNNer^［50］	39.60	16.20	35.30	—	—	—	—	—	—
BERTSUM^［56］	43.25	20.24	39.63	—	—	—	—	—	—
HiStruct+BERT-base^［63］	43.38	20.33	39.78	—	—	—	—	—	—
HiStruct+RoBERTa-base^［63］	43.65	20.54	40.03	—	—	—	—	—	—
DISCOBERT^［57］	43.77	20.85	40.67	—	—	—	—	—	—
HETERSUMGRAPH^［55］	42.95	19.76	39.23	45.15	15.78	41.29	—	—	—
PRESUM+DR_sup^［67］	—	—	—	46.57	17.10	42.44	—	—	—

模型	CNN/DM			Multi‑News			Xsum
模型	ROUGE_1	ROUGE_2	ROUGE_L	ROUGE_1	ROUGE_2	ROUGE_L	ROUGE_1	ROUGE_2	ROUGE_L
PEGASUS^［62］	44.17	21.47	41.11	—	—	—	47.21	24.56	39.25
SummaRuNNer^［50］	39.60	16.20	35.30	—	—	—	—	—	—
BERTSUM^［56］	43.25	20.24	39.63	—	—	—	—	—	—
HiStruct+BERT-base^［63］	43.38	20.33	39.78	—	—	—	—	—	—
HiStruct+RoBERTa-base^［63］	43.65	20.54	40.03	—	—	—	—	—	—
DISCOBERT^［57］	43.77	20.85	40.67	—	—	—	—	—	—
HETERSUMGRAPH^［55］	42.95	19.76	39.23	45.15	15.78	41.29	—	—	—
PRESUM+DR_sup^［67］	—	—	—	46.57	17.10	42.44	—	—	—

语言	数据集	摘要方式	规模（约）
英文	DUC/TAC	抽取式/生成式	0.97万
	CNN/DM	抽取式/生成式	30万
	CNEWSROOMS	抽取式/生成式	130万
	RNSum	抽取式/生成式	8.2万
	QMSum	抽取式/生成式	0.2万
	Multi-News	抽取式/生成式	5.6万
	Xsum	抽取式/生成式	22.6万
	NYTAC	抽取式	650万
	ASNAPR	生成式	3 500万
	Gigaword^［69］	生成式	400万
	Byte Cup	生成式	130万
中文	LCSTS^［70］	生成式	240万
中文	NLPCC	生成式	5万
藏文	Ti-SUM	抽取式/生成式	0.1万

Survey of extractive text summarization based on unsupervised learning and supervised learning

基于无监督学习和监督学习的抽取式文本摘要综述

RichHTML

PDF

Knowledge

Abstract

Cite this article

share this article

Figures/Tables 9

References 83

Related Articles 15

Recommended Articles

Metrics

评价方式	评价指标	类别	适用范围	优点	缺点
自动评价	SUPERT	无监督	多文档摘要	不需要人工撰写参考摘要，方法简单有效	忽略了句子的位置信息
	Pyramid	注释	单文档摘要	聚焦单词之间的关系，捕获原文本的复杂性	忽略了内容单元之间的依赖关系
	BLEU	监督	单文档摘要、机器翻译	易于计算，速度快，应用范围广	不考虑语义、句子结构，不能较好地处理形态丰富的语句，偏向较短的摘要
	ROUGR_N	监督	单文档摘要、多文档摘要和短摘要提取等	简洁且有词序	区分度不高，随着n‑gram的增大，值变小
	ROUGR_L	监督	单文档摘要、多文档摘要和短摘要提取等	反映句子级别的顺序，不需要制定 n‑gram的长度	仅考虑了最长公共子序列的长度
人工评价			单文档、长文档、多文档和短摘要提取等	评价结果更精确，更符合实际	耗时耗力，容易受外界因素的干扰

[1]	Rong HUANG, Junjie SONG, Shubo ZHOU, Hao LIU. Image aesthetic quality evaluation method based on self-supervised vision Transformer [J]. Journal of Computer Applications, 2024, 44(4): 1269-1276.
[2]	Rui JIANG, Wei LIU, Cheng CHEN, Tao LU. Asymmetric unsupervised end-to-end image deraining network [J]. Journal of Computer Applications, 2024, 44(3): 922-930.
[3]	Jian LIU, Chenchen YOU, Jinming CAO, Qiong ZENG, Changhe TU. Construction and application of 3D dataset of human grasping objects [J]. Journal of Computer Applications, 2024, 44(1): 278-284.
[4]	Yuning ZHANG, Abudukelimu ABULIZI, Tisheng MEI, Chun XU, Maierdana MAIMAITIREYIMU, Halidanmu ABUDUKELIMU, Yutao HOU. Anomaly detection method for skeletal X-ray images based on self-supervised feature extraction [J]. Journal of Computer Applications, 2024, 44(1): 175-181.
[5]	Ruiqi WANG, Shujuan JI, Ning CAO, Yajie GUO. Semi-supervised fake job advertisement detection model based on consistency training [J]. Journal of Computer Applications, 2023, 43(9): 2932-2939.
[6]	Xiang GUO, Wengang JIANG, Yuhang WANG. Encrypted traffic classification method based on improved Inception-ResNet [J]. Journal of Computer Applications, 2023, 43(8): 2471-2476.
[7]	Chungang HAN, Yonghui LIU. Face liveness detection algorithm based on GhostNet and feature fusion [J]. Journal of Computer Applications, 2023, 43(8): 2588-2592.
[8]	Yi WANG, Jie XIE, Jia CHENG, Liwei DOU. Review of object pose estimation in RGB images based on deep learning [J]. Journal of Computer Applications, 2023, 43(8): 2546-2555.
[9]	Shengwei MA, Ruizhang HUANG, Lina REN, Chuan LIN. Structured deep text clustering model based on multi-layer semantic fusion [J]. Journal of Computer Applications, 2023, 43(8): 2364-2369.
[10]	Menglin HUANG, Lei DUAN, Yuanhao ZHANG, Peiyan WANG, Renhao LI. Prompt learning based unsupervised relation extraction model [J]. Journal of Computer Applications, 2023, 43(7): 2010-2016.
[11]	Wenju LI, Mengying LI, Liu CUI, Wanghui CHU, Yi ZHANG, Hui GAO. Monocular depth estimation method based on pyramid split attention network [J]. Journal of Computer Applications, 2023, 43(6): 1736-1742.
[12]	Zhe XU, Zhihong WANG, Cunyu SHAN, Yaru SUN, Ying YANG. Unsupervised face forgery video detection based on reconstruction error [J]. Journal of Computer Applications, 2023, 43(5): 1571-1577.
[13]	Mengting GE, Minghua WAN. Feature extraction model based on neighbor supervised locally invariant robust principal component analysis [J]. Journal of Computer Applications, 2023, 43(4): 1013-1020.
[14]	Jin XIA, Zhengqun WANG, Shiming ZHU. Traffic flow prediction model based on time series decomposition [J]. Journal of Computer Applications, 2023, 43(4): 1129-1135.
[15]	Jiangfeng ZHANG, Tao YAN, Bin CHEN, Yuhua QIAN, Yantao SONG. Multi-depth-of-field 3D shape reconstruction with global spatio-temporal feature coupling [J]. Journal of Computer Applications, 2023, 43(3): 894-902.