{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,31]],"date-time":"2025-12-31T01:34:18Z","timestamp":1767144858184,"version":"build-2238731810"},"reference-count":53,"publisher":"Springer Science and Business Media LLC","issue":"6","license":[{"start":{"date-parts":[[2023,9,28]],"date-time":"2023-09-28T00:00:00Z","timestamp":1695859200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,9,28]],"date-time":"2023-09-28T00:00:00Z","timestamp":1695859200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["SN COMPUT. SCI."],"DOI":"10.1007\/s42979-023-02241-x","type":"journal-article","created":{"date-parts":[[2023,9,28]],"date-time":"2023-09-28T08:01:56Z","timestamp":1695888116000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["A Statistical Language Modeling Framework for Extractive Summarization of Text Documents"],"prefix":"10.1007","volume":"4","author":[{"given":"Pooja","family":"Gupta","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Swati","family":"Nigam","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4022-9945","authenticated-orcid":false,"given":"Rajiv","family":"Singh","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,9,28]]},"reference":[{"key":"2241_CR1","doi-asserted-by":"publisher","first-page":"113679","DOI":"10.1016\/j.eswa.2020.113679","volume":"165","author":"WS ElKassas","year":"2020","unstructured":"ElKassas WS, Salama CR, Rafea AA, Mohamed HK. Automatic text summarization: a comprehensive survey. Expert Syst Appl. 2021;165:113679.","journal-title":"Expert Syst Appl"},{"issue":"1","key":"2241_CR2","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s10462-016-9475-9","volume":"47","author":"M Gambhir","year":"2017","unstructured":"Gambhir M, Gupta V. Recent automatic text summarization techniques: a survey. Artif Intell Rev. 2017;47(1):1\u201366.","journal-title":"Artif Intell Rev"},{"issue":"14","key":"2241_CR3","doi-asserted-by":"publisher","first-page":"5755","DOI":"10.1016\/j.eswa.2013.04.023","volume":"40","author":"R Ferreira","year":"2013","unstructured":"Ferreira R, De Souza Cabral L, Lins RD, Silva GP, Freitas F, Cavalcanti GD, Favaro L. Assessing sentence scoring techniques for extractive text summarization. Expert Syst Appl. 2013;40(14):5755\u201364.","journal-title":"Expert Syst Appl"},{"issue":"3","key":"2241_CR4","first-page":"258","volume":"2","author":"V Gupta","year":"2010","unstructured":"Gupta V, Lehal GS. A survey of text summarization extractive techniques. J Emerg Technol Web Intell. 2010;2(3):258\u201368.","journal-title":"J Emerg Technol Web Intell"},{"key":"2241_CR5","first-page":"6399","volume":"33","author":"S Gao","year":"2019","unstructured":"Gao S, Chen X, Li P, Ren Z, Bing L, Zhao D, Yan R. Abstractive text summarization by incorporating reader comments. Proc AAAI Conf Artif Intell. 2019;33:6399\u2013406.","journal-title":"Proc AAAI Conf Artif Intell"},{"key":"2241_CR6","first-page":"205","volume-title":"Brazilian symposium on artificial intelligence","author":"JL Neto","year":"2002","unstructured":"Neto JL, Freitas AA, Kaestner CA. Automatic text summarization using a machine learning approach. In: Brazilian symposium on artificial intelligence. Berlin, Heidelberg: Springer; 2002. p. 205\u201315."},{"key":"2241_CR7","unstructured":"https:\/\/www.tensorflow.org\/datasets\/catalog\/cnn_dailymail. Accessed 29 July 2022."},{"key":"2241_CR8","unstructured":"https:\/\/www.kaggle.com\/pariza\/bbc-news-summary. Accessed 29 July 2022."},{"key":"2241_CR9","unstructured":"https:\/\/www.kaggle.com\/datasets\/usmanniazi\/duc-2004-dataset. Accessed 29 July 2022."},{"key":"2241_CR10","unstructured":"https:\/\/www.microsofttranslator.com. Accessed 01 Aug 2022."},{"key":"2241_CR11","unstructured":"https:\/\/translate.goolge.com. Accessed 01 Aug 2022."},{"key":"2241_CR12","unstructured":"https:\/\/www.systran.net\/en\/translate\/. Accessed 01 Aug 2022."},{"key":"2241_CR13","doi-asserted-by":"crossref","unstructured":"Lin CY, Hovy E. Automatic evaluation of summaries using n-gram co-occurrence statistics. In: Proceedings of the 2003 human language technology conference of the North American chapter of the association for computational linguistics. ACL; 2003. p. 150\u2013157.","DOI":"10.3115\/1073445.1073465"},{"key":"2241_CR14","doi-asserted-by":"crossref","unstructured":"Hong K, Nenkova A. Improving the estimation of word importance for news multi-document summarization. In: Proceedings of the 14th conference of the European chapter of the association for computational linguistics. ACL; 2014. p. 712\u2013721.","DOI":"10.3115\/v1\/E14-1075"},{"issue":"1","key":"2241_CR15","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s40537-022-00561-y","volume":"9","author":"A Chiche","year":"2022","unstructured":"Chiche A, Yitagesu B. Part of speech tagging: a systematic review of deep learning and machine learning approaches. J Big Data. 2022;9(1):1\u201325.","journal-title":"J Big Data"},{"issue":"1\u20132","key":"2241_CR16","first-page":"22","volume":"11","author":"JB Lovins","year":"1968","unstructured":"Lovins JB. Development of a stemming algorithm. Mech Transl Comput Linguist. 1968;11(1\u20132):22\u201331.","journal-title":"Mech Transl Comput Linguist"},{"key":"2241_CR17","doi-asserted-by":"crossref","unstructured":"Moratanch N, Chitrakala S. A survey on extractive text summarization. In: 2017 international conference on computer, communication and signal processing (ICCCSP) ACL. 2017. p. 1\u20136.","DOI":"10.1109\/ICCCSP.2017.7944061"},{"key":"2241_CR18","unstructured":"Lin CY. Rouge: a package for automatic evaluation of summaries. In: Text summarization branches out. IEEE; 2004. p. 74\u201381."},{"key":"2241_CR19","doi-asserted-by":"publisher","first-page":"137","DOI":"10.1007\/978-981-13-0514-6_14","volume-title":"Soft computing in data analytics","author":"C Mallick","year":"2019","unstructured":"Mallick C, Das AK, Dutta M, Das AK, Sarkar A. Graph-based text summarization using modified TextRank. In: Soft computing in data analytics. Singapore: Springer; 2019. p. 137\u201346."},{"issue":"2","key":"2241_CR20","first-page":"73","volume":"21","author":"R Elbarougy","year":"2020","unstructured":"Elbarougy R, Behery G, El Khatib A. Extractive Arabic text summarization using modified PageRank algorithm. Egypt Inf J. 2020;21(2):73\u201381.","journal-title":"Egypt Inf J"},{"key":"2241_CR21","doi-asserted-by":"crossref","unstructured":"Mihalcea R. Graph-based ranking algorithms for sentence extraction, applied to text summarization. In: Proceedings of the ACL interactive poster and demonstration sessions. ACL; 2004. p. 170\u2013173.","DOI":"10.3115\/1219044.1219064"},{"key":"2241_CR22","unstructured":"Radev DR, Allison T, Blair-Goldensohn S, Blitzer J, Celebi A, Dimitrov S, Zhang Z, MEAD-a platform for multidocument multilingual text summarization. In: Proceedings of the 4th international conference on language resources and evaluation. Lisbon, Portugal, 2004. p. 699\u2013702."},{"issue":"2","key":"2241_CR23","doi-asserted-by":"publisher","first-page":"59","DOI":"10.3390\/info11020059","volume":"11","author":"S Abdulateef","year":"2020","unstructured":"Abdulateef S, Khan NA, Chen B, Shang X. Multidocument Arabic text summarization based on clustering and Word2Vec to reduce redundancy. Information. 2020;11(2):59.","journal-title":"Information"},{"key":"2241_CR24","first-page":"51","volume-title":"International Conference on Applications of Natural Language to Information Systems","author":"H Oufaida","year":"2015","unstructured":"Oufaida H, Blache P, Nouali O. Using distributed word representations and mRMR discriminant analysis for multilingual text summarization. In: International Conference on Applications of Natural Language to Information Systems. Cham: Springer; 2015. p. 51\u201363."},{"key":"2241_CR25","doi-asserted-by":"crossref","unstructured":"Kaljahi R, Foster J, Roturier J. Semantic Role Labelling with minimal resources: Experiments with French. In: * SEM@ COLING. 2014. p. 87\u201392","DOI":"10.3115\/v1\/S14-1012"},{"key":"2241_CR26","doi-asserted-by":"publisher","first-page":"591","DOI":"10.1007\/978-3-642-15939-8_40","volume-title":"Joint European Conference on Machine Learning and Knowledge Discovery in Databases","author":"M Kabadjov","year":"2010","unstructured":"Kabadjov M, Atkinson M, Steinberger J, Steinberger R, Goot EVD. NewsGist: a multilingual statistical news summarizer. In: Joint European Conference on Machine Learning and Knowledge Discovery in Databases. Berlin, Heidelberg: Springer; 2010. p. 591\u20134."},{"key":"2241_CR27","doi-asserted-by":"publisher","first-page":"9353","DOI":"10.1007\/s10489-021-02871-9","volume":"52","author":"R Rani","year":"2022","unstructured":"Rani R, Lobiyal DK. Document vector embedding based extractive text summarization system for Hindi and English text. Appl Intell. 2022;52:9353\u201372.","journal-title":"Appl Intell"},{"issue":"2","key":"2241_CR28","doi-asserted-by":"publisher","first-page":"264","DOI":"10.1145\/321510.321519","volume":"16","author":"HP Edmundson","year":"1969","unstructured":"Edmundson HP. New methods in automatic extracting. JACM. 1969;16(2):264\u201385.","journal-title":"JACM"},{"issue":"2","key":"2241_CR29","doi-asserted-by":"publisher","first-page":"159","DOI":"10.1147\/rd.22.0159","volume":"2","author":"HP Luhn","year":"1958","unstructured":"Luhn HP. The automatic creation of literature abstracts. IBM J Res Dev. 1958;2(2):159\u201365.","journal-title":"IBM J Res Dev"},{"key":"2241_CR30","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3545176","volume":"55","author":"HY Koh","year":"2022","unstructured":"Koh HY, Ju J, Liu M, Pan S. An empirical survey on long document summarization: datasets, models, and metrics. ACM Comput Surv. 2022;55:1\u201335.","journal-title":"ACM Comput Surv"},{"key":"2241_CR31","doi-asserted-by":"publisher","first-page":"457","DOI":"10.1016\/j.jbi.2014.06.009","volume":"52","author":"R Mishra","year":"2014","unstructured":"Mishra R, Bian J, Fiszman M, Weir CR, Jonnalagadda S, Mostafa J, Del Fiol G. Text summarization in the biomedical domain: a systematic review of recent research. J Biomed Inf. 2014;52:457\u201367.","journal-title":"J Biomed Inf"},{"key":"2241_CR32","doi-asserted-by":"publisher","first-page":"128","DOI":"10.1109\/ICWR.2018.8387248","volume-title":"2018 4th international conference on web research (ICWR)","author":"M Afsharizadeh","year":"2018","unstructured":"Afsharizadeh M, Ebrahimpour-Komleh H, Bagheri A. Query-oriented text summarization using sentence extraction technique. In: 2018 4th international conference on web research (ICWR). IEEE; 2018. p. 128\u201332."},{"issue":"17","key":"2241_CR33","doi-asserted-by":"publisher","first-page":"e5206","DOI":"10.1002\/cpe.5206","volume":"31","author":"K Yang","year":"2019","unstructured":"Yang K, He H, Al.Sabahi K, Zhang Z. EcForest: extractive document summarization through enhanced sentence embedding and cascade forest. Concurr Comput Pract Exp. 2019;31(17):e5206.","journal-title":"Concurr Comput Pract Exp"},{"key":"2241_CR34","doi-asserted-by":"publisher","first-page":"93","DOI":"10.1016\/j.eswa.2016.10.017","volume":"68","author":"M Yousefi-Azar","year":"2017","unstructured":"Yousefi-Azar M, Hamey L. Text summarization using unsupervised deep learning. Expert Syst Appl. 2017;68:93\u2013105.","journal-title":"Expert Syst Appl"},{"key":"2241_CR35","doi-asserted-by":"publisher","first-page":"457","DOI":"10.1613\/jair.1523","volume":"22","author":"G Erkan","year":"2004","unstructured":"Erkan G, Radev DR. Lexrank: graph-based lexical centrality as salience in text summarization. J Artif Intell Res. 2004;22:457\u201379.","journal-title":"J Artif Intell Res"},{"key":"2241_CR36","unstructured":"https:\/\/www.nltk.org\/nltk_data\/. Accessed 02 Aug 2022"},{"key":"2241_CR37","unstructured":"Shrivastava M, Bhattacharyya P, Hindi POS tagger using naive stemming: harnessing morphological information without extensive linguistic knowledge. In: International Conference on NLP (ICON08). Pune, India. ACL; 2008."},{"issue":"3","key":"2241_CR38","doi-asserted-by":"publisher","first-page":"130","DOI":"10.1108\/eb046814","volume":"14","author":"MF Porter","year":"1980","unstructured":"Porter MF. An algorithm for suffix stripping program: electronic library and information systems. Program. 1980;14(3):130\u20137.","journal-title":"Program"},{"issue":"4","key":"2241_CR39","doi-asserted-by":"publisher","first-page":"3925","DOI":"10.1007\/s13369-020-05258-z","volume":"46","author":"A Chouigui","year":"2021","unstructured":"Chouigui A, Ben Khiroun O, Elayeb B. An arabic multi-source news corpus: experimenting on single-document extractive summarization. Arab J Sci Eng. 2021;46(4):3925\u201338.","journal-title":"Arab J Sci Eng"},{"issue":"12","key":"2241_CR40","doi-asserted-by":"publisher","first-page":"7803","DOI":"10.1007\/s13369-018-3198-y","volume":"43","author":"N Alami","year":"2018","unstructured":"Alami N, En-nahnahi N, Ouatik SA, Meknassi M. Using unsupervised deep learning for automatic summarization of Arabic documents. Arab J Sci Eng. 2018;43(12):7803\u201315.","journal-title":"Arab J Sci Eng"},{"key":"2241_CR41","unstructured":"http:\/\/www-nlpir.nist.gov\/related_projects\/tipster_summac\/cmp_lg.html. Accessed 07 Dec 2022."},{"key":"2241_CR42","unstructured":"https:\/\/catalog.ldc.upenn.edu\/LDC2003T05. Accessed 07 Dec 2022."},{"key":"2241_CR43","unstructured":"Koupaee M, Wang Y. WikiHow: a large scale text summarization dataset. arXiv preprint. arXiv:1810.09305 (2018)"},{"key":"2241_CR44","first-page":"101","volume-title":"The impact of frequency on summarization","author":"A Nenkova","year":"2005","unstructured":"Nenkova A, Vanderwende L. The impact of frequency on summarization. Redmond: Microsoft Research; 2005. p. 101."},{"key":"2241_CR45","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2022.116846","volume":"200","author":"A Joshi","year":"2022","unstructured":"Joshi A, Fidalgo E, Alegre E, Alaiz-Rodriguez R. RankSum\u2014an unsupervised extractive text summarization based on rank fusion. Expert Syst Appl. 2022;200: 116846.","journal-title":"Expert Syst Appl"},{"key":"2241_CR46","doi-asserted-by":"publisher","first-page":"200","DOI":"10.1016\/j.eswa.2019.03.045","volume":"129","author":"A Joshi","year":"2019","unstructured":"Joshi A, Fidalgo E, Alegre E, Fern\u00e1ndez-Robles L. SummCoder: an unsupervised framework for extractive text summarization based on deep auto-encoders. Expert Syst Appl. 2019;129:200\u201315.","journal-title":"Expert Syst Appl"},{"key":"2241_CR47","doi-asserted-by":"crossref","unstructured":"Abualigah L, Bashabsheh MQ, Alabool H, Shehab M. Text summarization: a brief review. In: Recent Advances in NLP: the case of Arabic language. Cham: ACL; 2020. p. 1\u201315.","DOI":"10.1007\/978-3-030-34614-0_1"},{"key":"2241_CR48","doi-asserted-by":"crossref","unstructured":"Bialy AA, Gaheen MA, ElEraky RM, ElGamal AF, Ewees AA, Single Arabic document summarization using natural language processing technique. In: Recent Advances in NLP: The Case of Arabic Language. Cham: ACL; 2020. p. 17\u201337.","DOI":"10.1007\/978-3-030-34614-0_2"},{"key":"2241_CR49","doi-asserted-by":"publisher","first-page":"391","DOI":"10.1016\/j.procs.2021.01.021","volume":"179","author":"MF Fakhrezi","year":"2021","unstructured":"Fakhrezi MF, Bijaksana MA, Huda AF. Implementation of automatic text summarization with TextRank method in the development of Al-qur\u2019an vocabulary encyclopedia. Procedia Computer Science. 2021;179:391\u20138.","journal-title":"Procedia Computer Science"},{"key":"2241_CR50","doi-asserted-by":"crossref","unstructured":"Yadav D, Desai J, Yadav AK. Automatic text summarization methods: a comprehensive review. 2022. arXiv preprint arXiv:2204.01849","DOI":"10.1109\/ACCESS.2022.3231016"},{"key":"2241_CR51","doi-asserted-by":"publisher","first-page":"38012","DOI":"10.1109\/ACCESS.2022.3163292","volume":"10","author":"A Elsaid","year":"2022","unstructured":"Elsaid A, Mohammed A, Ibrahim LF, Sakre MM. A comprehensive review of arabic text summarization. IEEE Access. 2022;10:38012\u201330.","journal-title":"IEEE Access"},{"issue":"2","key":"2241_CR52","doi-asserted-by":"publisher","first-page":"372","DOI":"10.3390\/electronics12020372","volume":"12","author":"V Gulati","year":"2023","unstructured":"Gulati V, Kumar D, Popescu DE, Hemanth JD. Extractive article summarization using integrated TextRank and BM25+ algorithm. Electronics. 2023;12(2):372.","journal-title":"Electronics"},{"key":"2241_CR53","unstructured":"Cajueiro DO, Nery AG, Tavares I, De Melo MK, Reis SAD, Weigang L, Celestino VR. A comprehensive review of automatic text summarization techniques: method, data, evaluation and coding. 2023. arXiv:2301.03403"}],"updated-by":[{"DOI":"10.1007\/s42979-023-02456-y","type":"correction","label":"Correction","source":"publisher","updated":{"date-parts":[[2023,11,8]],"date-time":"2023-11-08T00:00:00Z","timestamp":1699401600000}}],"container-title":["SN Computer Science"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s42979-023-02241-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s42979-023-02241-x\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s42979-023-02241-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,8]],"date-time":"2023-11-08T07:25:25Z","timestamp":1699428325000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s42979-023-02241-x"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,9,28]]},"references-count":53,"journal-issue":{"issue":"6","published-online":{"date-parts":[[2023,11]]}},"alternative-id":["2241"],"URL":"https:\/\/doi.org\/10.1007\/s42979-023-02241-x","relation":{},"ISSN":["2661-8907"],"issn-type":[{"value":"2661-8907","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,9,28]]},"assertion":[{"value":"5 February 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"9 August 2023","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"28 September 2023","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"8 November 2023","order":4,"name":"change_date","label":"Change Date","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"Correction","order":5,"name":"change_type","label":"Change Type","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"A Correction to this paper has been published:","order":6,"name":"change_details","label":"Change Details","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"https:\/\/doi.org\/10.1007\/s42979-023-02456-y","URL":"https:\/\/doi.org\/10.1007\/s42979-023-02456-y","order":7,"name":"change_details","label":"Change Details","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare that there is no conflict of interest regarding this manuscript and received no funding for this work.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of Interest"}}],"article-number":"750"}}