{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,13]],"date-time":"2026-01-13T23:26:51Z","timestamp":1768346811256,"version":"3.49.0"},"publisher-location":"New York, NY, USA","reference-count":31,"publisher":"ACM","license":[{"start":{"date-parts":[[2019,9,23]],"date-time":"2019-09-23T00:00:00Z","timestamp":1569196800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"Coordena\u00e7\u00e3o de Aperfei\u00e7oamento de Pessoal de N\u00edvel Superior"},{"name":"Conselho Nacional de Desenvolvimento Cient\u00edfico e Tecnol\u00f3gico"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2019,9,23]]},"DOI":"10.1145\/3342558.3345388","type":"proceedings-article","created":{"date-parts":[[2019,9,19]],"date-time":"2019-09-19T15:34:36Z","timestamp":1568907276000},"page":"1-10","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":13,"title":["The CNN-Corpus"],"prefix":"10.1145","author":[{"given":"Rafael Dueire","family":"Lins","sequence":"first","affiliation":[{"name":"UFPE\/UFRPE, Recife, Brazil"}]},{"given":"Hilario","family":"Oliveira","sequence":"additional","affiliation":[{"name":"UFPE, Recife, Brazil"}]},{"given":"Luciano","family":"Cabral","sequence":"additional","affiliation":[{"name":"UFPE, Recife, Brazil"}]},{"given":"Jamilson","family":"Batista","sequence":"additional","affiliation":[{"name":"UFPE, Recife, Brazil"}]},{"given":"Bruno","family":"Tenorio","sequence":"additional","affiliation":[{"name":"UFPE, Recife, Brazil"}]},{"given":"Rafael","family":"Ferreira","sequence":"additional","affiliation":[{"name":"UFRPE, Recife, Brazil"}]},{"given":"Rinaldo","family":"Lima","sequence":"additional","affiliation":[{"name":"UFRPE, Recife, Brazil"}]},{"given":"Gabriel","family":"de Fran\u00e7a Pereira e Silva","sequence":"additional","affiliation":[{"name":"UFRPE, Recife, Brazil"}]},{"given":"Steven J.","family":"Simske","sequence":"additional","affiliation":[{"name":"Colorado State University, Fort Collins, CO, USA"}]}],"member":"320","published-online":{"date-parts":[[2019,9,23]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1145\/2960811.2967159"},{"key":"e_1_3_2_1_2_1","volume-title":"Proceedings of the 2014 ACM symposium on Document engineering - DocEng '14","author":"de Souza Cabral Luciano","year":"2014","unstructured":"Luciano de Souza Cabral , Rafael Dueire Lins , Rafael Fe Mello , Fred Freitas , Bruno \u00c1vila , Steven Simske , and Marcelo Riss . 2014 . A platform for language independent summarization . In Proceedings of the 2014 ACM symposium on Document engineering - DocEng '14 . ACM Press, New York, New York, USA, 203--206. https:\/\/doi.org\/10.1145\/2644866.2644890 10.1145\/2644866.2644890 Luciano de Souza Cabral, Rafael Dueire Lins, Rafael Fe Mello, Fred Freitas, Bruno \u00c1vila, Steven Simske, and Marcelo Riss. 2014. A platform for language independent summarization. In Proceedings of the 2014 ACM symposium on Document engineering - DocEng '14. ACM Press, New York, New York, USA, 203--206. https:\/\/doi.org\/10.1145\/2644866.2644890"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/321510.321519"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2014.03.023"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2013.04.023"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/WI-IAT.2013.55"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/DAS.2014.19"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/WI-IAT.2014.23"},{"key":"e_1_3_2_1_9_1","volume-title":"Recent automatic text summarization techniques: a survey. Artificial Intelligence Review","author":"Gambhir Mahak","year":"2016","unstructured":"Mahak Gambhir and Vishal Gupta . 2016. Recent automatic text summarization techniques: a survey. Artificial Intelligence Review ( 2016 ), 1--66. Mahak Gambhir and Vishal Gupta. 2016. Recent automatic text summarization techniques: a survey. Artificial Intelligence Review (2016), 1--66."},{"key":"e_1_3_2_1_10_1","unstructured":"Pierre-Etienne Genest. 2013. G\u00e9n\u00e9ration de r\u00e9sum\u00e9s par abstraction. Thesis in French. Universit\u00e9 de Montr\u00e9al G\u00e9n\u00e9ration.  Pierre-Etienne Genest. 2013. G\u00e9n\u00e9ration de r\u00e9sum\u00e9s par abstraction. Thesis in French. Universit\u00e9 de Montr\u00e9al G\u00e9n\u00e9ration."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.4304\/jetwi.2.3.258-268"},{"key":"e_1_3_2_1_12_1","volume-title":"Proceedings of Corpus Linguistics","author":"Hasler Laura","year":"2003","unstructured":"Laura Hasler , Constantin Orasan , and Ruslan Mitkov . 2003 . Building better corpora for summarisation . In Proceedings of Corpus Linguistics 2003. 309--319. Laura Hasler, Constantin Orasan, and Ruslan Mitkov. 2003. Building better corpora for summarisation. In Proceedings of Corpus Linguistics 2003. 309--319."},{"key":"e_1_3_2_1_13_1","volume-title":"Proceedings of the 22nd annual international ACM SIGIR conference on Research and development in information retrieval - SIGIR '99. ACM Press","author":"Jing Hongyan","unstructured":"Hongyan Jing and Kathleen R . McKeown. 1999. The decomposition of human-written summary sentences . In Proceedings of the 22nd annual international ACM SIGIR conference on Research and development in information retrieval - SIGIR '99. ACM Press , New York, New York, USA, 129--136. Hongyan Jing and Kathleen R. McKeown. 1999. The decomposition of human-written summary sentences. In Proceedings of the 22nd annual international ACM SIGIR conference on Research and development in information retrieval - SIGIR '99. ACM Press, New York, New York, USA, 129--136."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/215206.215333"},{"key":"e_1_3_2_1_15_1","volume-title":"Indexing and Abstracting in Theory and Practice (3 ed.)","author":"Lancaster F. W.","unstructured":"F. W. Lancaster . 2003. Indexing and Abstracting in Theory and Practice (3 ed.) . Library Association , London . F. W. Lancaster. 2003. Indexing and Abstracting in Theory and Practice (3 ed.). Library Association, London."},{"key":"e_1_3_2_1_16_1","first-page":"707","article-title":"Binary Codes Capable of Correcting Deletions, Insertions and Reversals","volume":"10","author":"Levenshtein VI","year":"1966","unstructured":"VI Levenshtein . 1966 . Binary Codes Capable of Correcting Deletions, Insertions and Reversals . Soviet Physics Doklady 10 (1966), 707 . VI Levenshtein. 1966. Binary Codes Capable of Correcting Deletions, Insertions and Reversals. Soviet Physics Doklady 10 (1966), 707.","journal-title":"Soviet Physics Doklady"},{"key":"e_1_3_2_1_17_1","volume-title":"Proceedings of the 2019 ACM Symposium on Document Engineering (DocEng '19)","author":"Lins Rafael Dueire","year":"1874","unstructured":"Rafael Dueire Lins , Rafael Ferreira , and Steven J. Simske . 2019. DocEng'19 Competition on Extractive Text Summarization . In Proceedings of the 2019 ACM Symposium on Document Engineering (DocEng '19) . ACM, New York, NY, USA, 216--217. https:\/\/doi.org\/10.1145\/3342558.335 1874 10.1145\/3342558.3351874 Rafael Dueire Lins, Rafael Ferreira, and Steven J. Simske. 2019. DocEng'19 Competition on Extractive Text Summarization. In Proceedings of the 2019 ACM Symposium on Document Engineering (DocEng '19). ACM, New York, NY, USA, 216--217. https:\/\/doi.org\/10.1145\/3342558.3351874"},{"key":"e_1_3_2_1_18_1","volume-title":"Proceedings of the 2019 ACM Symposium on Document Engineering (DocEng '19)","author":"Lins Rafael Dueire","unstructured":"Rafael Dueire Lins , Hilario Oliveira , Bruno Tenorio , Jamilson Batista , Rafael Ferreira , Gabriel Pereira e Silva , Rinaldo Lima , Diego Salcedo , and Steven J. Simske . 2019. The CNN-Corpus in Spanish: a Large Corpus for Extractive Text Summarization in the Spanish Language . In Proceedings of the 2019 ACM Symposium on Document Engineering (DocEng '19) . ACM, New York, NY, USA, 211--215. https:\/\/doi.org\/10.1145\/3342558.3345423 10.1145\/3342558.3345423 Rafael Dueire Lins,Hilario Oliveira,Bruno Tenorio,Jamilson Batista,Rafael Ferreira, Gabriel Pereira e Silva, Rinaldo Lima, Diego Salcedo, and Steven J. Simske. 2019. The CNN-Corpus in Spanish: a Large Corpus for Extractive Text Summarization in the Spanish Language. In Proceedings of the 2019 ACM Symposium on Document Engineering (DocEng '19). ACM, New York, NY, USA, 211--215. https:\/\/doi.org\/10.1145\/3342558.3345423"},{"key":"e_1_3_2_1_19_1","volume-title":"11st IADIS international conference WWW and INTERNET","author":"Lins Rafael Dueire","year":"2012","unstructured":"Rafael Dueire Lins , Steven J Simske , Luciano de Souza Cabral , Gabriel de Fran\u00e7a Pereira e Silva , Rinaldo Lima , Rafael Ferreira de Mello , and Luciano Favaro . 2012 . A multi-tool scheme for summarizing textual documents . In 11st IADIS international conference WWW and INTERNET 2012. Madrid, Spain, 1--8. Rafael Dueire Lins, Steven J Simske, Luciano de Souza Cabral, Gabriel de Fran\u00e7a Pereira e Silva, Rinaldo Lima, Rafael Ferreira de Mello, and Luciano Favaro. 2012. A multi-tool scheme for summarizing textual documents. In 11st IADIS international conference WWW and INTERNET 2012. Madrid, Spain, 1--8."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1147\/rd.22.0159"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/312624.312668"},{"key":"e_1_3_2_1_22_1","volume-title":"A Survey of Text Summarization Techniques","author":"Nenkova Ani","unstructured":"Ani Nenkova and Kathleen McKeown . 2012. A Survey of Text Summarization Techniques . In Mining Text Data, Charu C. Aggarwal and ChengXiang Zhai (Eds.). Springer US , Boston, MA , 43--76. https:\/\/doi.org\/10.1007\/978-1-4614-3223-4_3 10.1007\/978-1-4614-3223-4_3 Ani Nenkova and Kathleen McKeown. 2012. A Survey of Text Summarization Techniques. In Mining Text Data, Charu C. Aggarwal and ChengXiang Zhai (Eds.). Springer US, Boston, MA, 43--76. https:\/\/doi.org\/10.1007\/978-1-4614-3223-4_3"},{"key":"e_1_3_2_1_23_1","volume-title":"Third International Conference on Language Resources and Evaluation (LREC). Las Palmas de Gran Canaria, 1780--1786","author":"Orasan C","year":"2002","unstructured":"C Orasan . 2002 . Building annotated resources for automatic text summarisation . In Third International Conference on Language Resources and Evaluation (LREC). Las Palmas de Gran Canaria, 1780--1786 . C Orasan. 2002. Building annotated resources for automatic text summarisation. In Third International Conference on Language Resources and Evaluation (LREC). Las Palmas de Gran Canaria, 1780--1786."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.5555\/1944566.1944672"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ipm.2007.01.019"},{"key":"e_1_3_2_1_26_1","volume-title":"DUC: An Intrinsic Evaluation of Generic News Text Summarization Systems","author":"Over P.","year":"2002","unstructured":"P. Over and W. Liggett . 2002 . Introduction to DUC: An Intrinsic Evaluation of Generic News Text Summarization Systems . http:\/\/www-nlpir.nist.gov\/projects\/duc\/pubs\/2002slides\/overview.02.pdf, last visited on 18th March 2019. (2002). P. Over and W. Liggett. 2002. Introduction to DUC: An Intrinsic Evaluation of Generic News Text Summarization Systems. http:\/\/www-nlpir.nist.gov\/projects\/duc\/pubs\/2002slides\/overview.02.pdf, last visited on 18th March 2019. (2002)."},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.3115\/1075096.1075144"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1002\/asi.4630220405"},{"key":"e_1_3_2_1_29_1","volume-title":"Proceedings of the ACM Symposium on Document Engineering 2018","author":"Steven","year":"2018","unstructured":"Steven J. Simske and Rafael Dueire Lins. 2018. Automatic Text Summarization and Classification . In Proceedings of the ACM Symposium on Document Engineering 2018 , DocEng 2018 , Halifax, NS, Canada, August 28-31, 2018. 1:1--1:2. https:\/\/doi.org\/10.1145\/3209280.3232791 10.1145\/3209280.3232791 Steven J. Simske and Rafael Dueire Lins. 2018. Automatic Text Summarization and Classification. In Proceedings of the ACM Symposium on Document Engineering 2018, DocEng 2018, Halifax, NS, Canada, August 28-31, 2018. 1:1--1:2. https:\/\/doi.org\/10.1145\/3209280.3232791"},{"key":"e_1_3_2_1_30_1","unstructured":"Krysta M Svore L Vanderwende and CJC Burges. 2007. Enhancing Single-Document Summarization by Combining RankNet and Third-Party Sources.. In EMNLP-CoNLL. Prague Czech Republic 448--457.  Krysta M Svore L Vanderwende and CJC Burges. 2007. Enhancing Single-Document Summarization by Combining RankNet and Third-Party Sources.. In EMNLP-CoNLL. Prague Czech Republic 448--457."},{"key":"e_1_3_2_1_31_1","volume-title":"Proceedings of the ACL'97\/EACL'97 Workshop pn Intelligent Scallable Text Summarization. Madrid, 58--59","author":"Teufel Simone","year":"1997","unstructured":"Simone Teufel and Marc Moens . 1997 . Sentence Extraction as a Classification Task . In Proceedings of the ACL'97\/EACL'97 Workshop pn Intelligent Scallable Text Summarization. Madrid, 58--59 . Simone Teufel and Marc Moens. 1997. Sentence Extraction as a Classification Task. In Proceedings of the ACL'97\/EACL'97 Workshop pn Intelligent Scallable Text Summarization. Madrid, 58--59."}],"event":{"name":"DocEng '19: ACM Symposium on Document Engineering 2019","location":"Berlin Germany","acronym":"DocEng '19","sponsor":["SIGWEB ACM Special Interest Group on Hypertext, Hypermedia, and Web","SIGDOC ACM Special Interest Group for Design of Communications"]},"container-title":["Proceedings of the ACM Symposium on Document Engineering 2019"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3342558.3345388","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3342558.3345388","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T23:23:00Z","timestamp":1750202580000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3342558.3345388"}},"subtitle":["A Large Textual Corpus for Single-Document Extractive Summarization"],"short-title":[],"issued":{"date-parts":[[2019,9,23]]},"references-count":31,"alternative-id":["10.1145\/3342558.3345388","10.1145\/3342558"],"URL":"https:\/\/doi.org\/10.1145\/3342558.3345388","relation":{},"subject":[],"published":{"date-parts":[[2019,9,23]]},"assertion":[{"value":"2019-09-23","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}