{"id":"https://openalex.org/W2974327368","doi":"https://doi.org/10.1145/3342558.3345388","title":"The CNN-Corpus","display_name":"The CNN-Corpus","publication_year":2019,"publication_date":"2019-09-19","ids":{"openalex":"https://openalex.org/W2974327368","doi":"https://doi.org/10.1145/3342558.3345388","mag":"2974327368"},"language":"en","primary_location":{"id":"doi:10.1145/3342558.3345388","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3342558.3345388","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM Symposium on Document Engineering 2019","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5042210961","display_name":"Rafael Dueire Lins","orcid":"https://orcid.org/0000-0003-3497-5044"},"institutions":[{"id":"https://openalex.org/I4210138879","display_name":"Hospital das Cl\u00ednicas da Universidade Federal de Pernambuco","ror":"https://ror.org/03rehvw54","country_code":"BR","type":"healthcare","lineage":["https://openalex.org/I4210138879"]},{"id":"https://openalex.org/I62921916","display_name":"Universidade Federal Rural de Pernambuco","ror":"https://ror.org/02ksmb993","country_code":"BR","type":"education","lineage":["https://openalex.org/I62921916"]}],"countries":["BR"],"is_corresponding":true,"raw_author_name":"Rafael Dueire Lins","raw_affiliation_strings":["UFPE/UFRPE, Recife, Brazil"],"affiliations":[{"raw_affiliation_string":"UFPE/UFRPE, Recife, Brazil","institution_ids":["https://openalex.org/I4210138879","https://openalex.org/I62921916"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029524369","display_name":"Hil\u00e1rio Oliveira","orcid":"https://orcid.org/0000-0003-0643-7206"},"institutions":[{"id":"https://openalex.org/I4210138879","display_name":"Hospital das Cl\u00ednicas da Universidade Federal de Pernambuco","ror":"https://ror.org/03rehvw54","country_code":"BR","type":"healthcare","lineage":["https://openalex.org/I4210138879"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Hilario Oliveira","raw_affiliation_strings":["UFPE, Recife, Brazil"],"affiliations":[{"raw_affiliation_string":"UFPE, Recife, Brazil","institution_ids":["https://openalex.org/I4210138879"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055774687","display_name":"Luciano Cabral","orcid":"https://orcid.org/0000-0002-4235-5753"},"institutions":[{"id":"https://openalex.org/I4210138879","display_name":"Hospital das Cl\u00ednicas da Universidade Federal de Pernambuco","ror":"https://ror.org/03rehvw54","country_code":"BR","type":"healthcare","lineage":["https://openalex.org/I4210138879"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Luciano Cabral","raw_affiliation_strings":["UFPE, Recife, Brazil"],"affiliations":[{"raw_affiliation_string":"UFPE, Recife, Brazil","institution_ids":["https://openalex.org/I4210138879"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051005044","display_name":"Jamilson Batista","orcid":null},"institutions":[{"id":"https://openalex.org/I4210138879","display_name":"Hospital das Cl\u00ednicas da Universidade Federal de Pernambuco","ror":"https://ror.org/03rehvw54","country_code":"BR","type":"healthcare","lineage":["https://openalex.org/I4210138879"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Jamilson Batista","raw_affiliation_strings":["UFPE, Recife, Brazil"],"affiliations":[{"raw_affiliation_string":"UFPE, Recife, Brazil","institution_ids":["https://openalex.org/I4210138879"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021296367","display_name":"Bruno Tenorio","orcid":null},"institutions":[{"id":"https://openalex.org/I4210138879","display_name":"Hospital das Cl\u00ednicas da Universidade Federal de Pernambuco","ror":"https://ror.org/03rehvw54","country_code":"BR","type":"healthcare","lineage":["https://openalex.org/I4210138879"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Bruno Tenorio","raw_affiliation_strings":["UFPE, Recife, Brazil"],"affiliations":[{"raw_affiliation_string":"UFPE, Recife, Brazil","institution_ids":["https://openalex.org/I4210138879"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101430598","display_name":"Rafael Ferreira","orcid":"https://orcid.org/0000-0002-0448-0000"},"institutions":[{"id":"https://openalex.org/I62921916","display_name":"Universidade Federal Rural de Pernambuco","ror":"https://ror.org/02ksmb993","country_code":"BR","type":"education","lineage":["https://openalex.org/I62921916"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Rafael Ferreira","raw_affiliation_strings":["UFRPE, Recife, Brazil"],"affiliations":[{"raw_affiliation_string":"UFRPE, Recife, Brazil","institution_ids":["https://openalex.org/I62921916"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021095237","display_name":"Rinaldo Lima","orcid":"https://orcid.org/0000-0002-1388-4824"},"institutions":[{"id":"https://openalex.org/I62921916","display_name":"Universidade Federal Rural de Pernambuco","ror":"https://ror.org/02ksmb993","country_code":"BR","type":"education","lineage":["https://openalex.org/I62921916"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Rinaldo Lima","raw_affiliation_strings":["UFRPE, Recife, Brazil"],"affiliations":[{"raw_affiliation_string":"UFRPE, Recife, Brazil","institution_ids":["https://openalex.org/I62921916"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026670686","display_name":"Gabriel de Fran\u00e7a Pereira e Silva","orcid":null},"institutions":[{"id":"https://openalex.org/I62921916","display_name":"Universidade Federal Rural de Pernambuco","ror":"https://ror.org/02ksmb993","country_code":"BR","type":"education","lineage":["https://openalex.org/I62921916"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Gabriel de Fran\u00e7a Pereira e Silva","raw_affiliation_strings":["UFRPE, Recife, Brazil"],"affiliations":[{"raw_affiliation_string":"UFRPE, Recife, Brazil","institution_ids":["https://openalex.org/I62921916"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5022519243","display_name":"Steven J. Simske","orcid":null},"institutions":[{"id":"https://openalex.org/I92446798","display_name":"Colorado State University","ror":"https://ror.org/03k1gpj17","country_code":"US","type":"education","lineage":["https://openalex.org/I92446798"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Steven J. Simske","raw_affiliation_strings":["Colorado State University, Fort Collins, CO, USA"],"affiliations":[{"raw_affiliation_string":"Colorado State University, Fort Collins, CO, USA","institution_ids":["https://openalex.org/I92446798"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":9,"corresponding_author_ids":["https://openalex.org/A5042210961"],"corresponding_institution_ids":["https://openalex.org/I4210138879","https://openalex.org/I62921916"],"apc_list":null,"apc_paid":null,"fwci":0.8401,"has_fulltext":false,"cited_by_count":15,"citation_normalized_percentile":{"value":0.80555911,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"10"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9997000098228455,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9886000156402588,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/automatic-summarization","display_name":"Automatic summarization","score":0.9152030944824219},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8434760570526123},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.7443687915802002},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6855798959732056},{"id":"https://openalex.org/keywords/corpus-linguistics","display_name":"Corpus linguistics","score":0.6106609106063843},{"id":"https://openalex.org/keywords/text-corpus","display_name":"Text corpus","score":0.49478310346603394},{"id":"https://openalex.org/keywords/multi-document-summarization","display_name":"Multi-document summarization","score":0.43115517497062683},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3902357220649719}],"concepts":[{"id":"https://openalex.org/C170858558","wikidata":"https://www.wikidata.org/wiki/Q1394144","display_name":"Automatic summarization","level":2,"score":0.9152030944824219},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8434760570526123},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.7443687915802002},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6855798959732056},{"id":"https://openalex.org/C532629269","wikidata":"https://www.wikidata.org/wiki/Q865083","display_name":"Corpus linguistics","level":2,"score":0.6106609106063843},{"id":"https://openalex.org/C2474386","wikidata":"https://www.wikidata.org/wiki/Q461183","display_name":"Text corpus","level":2,"score":0.49478310346603394},{"id":"https://openalex.org/C134714966","wikidata":"https://www.wikidata.org/wiki/Q6934448","display_name":"Multi-document summarization","level":3,"score":0.43115517497062683},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3902357220649719}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3342558.3345388","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3342558.3345388","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM Symposium on Document Engineering 2019","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.7300000190734863}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W155542438","https://openalex.org/W1647671624","https://openalex.org/W1974339500","https://openalex.org/W1978264551","https://openalex.org/W1996333538","https://openalex.org/W1999837683","https://openalex.org/W2007407316","https://openalex.org/W2014524246","https://openalex.org/W2032266980","https://openalex.org/W2040904574","https://openalex.org/W2056609756","https://openalex.org/W2069618502","https://openalex.org/W2081056190","https://openalex.org/W2098618819","https://openalex.org/W2101390659","https://openalex.org/W2133750501","https://openalex.org/W2155871583","https://openalex.org/W2166347079","https://openalex.org/W2169401582","https://openalex.org/W2218641061","https://openalex.org/W2317879529","https://openalex.org/W2403275672","https://openalex.org/W2516641875","https://openalex.org/W2622651563","https://openalex.org/W2895770495","https://openalex.org/W2973444601","https://openalex.org/W2974107452","https://openalex.org/W3035219831"],"related_works":["https://openalex.org/W2104677027","https://openalex.org/W3164984162","https://openalex.org/W2902627734","https://openalex.org/W2112885393","https://openalex.org/W1990695371","https://openalex.org/W2173208124","https://openalex.org/W2099859325","https://openalex.org/W2065541085","https://openalex.org/W2568827738","https://openalex.org/W2365100044"],"abstract_inverted_index":{"This":[0],"paper":[1],"details":[2],"the":[3,6,10,13,31],"features":[4],"and":[5,38,45,53],"methodology":[7],"adopted":[8],"in":[9,36],"construction":[11],"of":[12,24,30,40,56],"CNN-corpus,":[14],"a":[15],"test":[16],"corpus":[17,50],"for":[18],"single":[19],"document":[20],"extractive":[21,47,57],"text":[22],"summarization":[23,58],"news":[25],"articles.":[26],"The":[27,49],"current":[28],"version":[29],"CNN-corpus":[32],"encompasses":[33],"3,000":[34],"texts":[35],"English,":[37],"each":[39],"them":[41],"has":[42],"an":[43,46],"abstractive":[44],"summary.":[48],"allows":[51],"quantitative":[52],"qualitative":[54],"assessments":[55],"strategies.":[59]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":3},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2019-09-26T00:00:00"}
