{"id":"https://openalex.org/W4312620285","doi":"https://doi.org/10.1109/icpr56361.2022.9956691","title":"NEWSFARM: A Large-Scale Chinese Corpus of Long News Summarization","display_name":"NEWSFARM: A Large-Scale Chinese Corpus of Long News Summarization","publication_year":2022,"publication_date":"2022-08-21","ids":{"openalex":"https://openalex.org/W4312620285","doi":"https://doi.org/10.1109/icpr56361.2022.9956691"},"language":"en","primary_location":{"id":"doi:10.1109/icpr56361.2022.9956691","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icpr56361.2022.9956691","pdf_url":null,"source":{"id":"https://openalex.org/S4363607731","display_name":"2022 26th International Conference on Pattern Recognition (ICPR)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 26th International Conference on Pattern Recognition (ICPR)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5027792289","display_name":"Shunan Zang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210156404","display_name":"Institute of Information Engineering","ror":"https://ror.org/04r53se39","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shunan Zang","raw_affiliation_strings":["Institute of Information Engineering,Beijing","Institute of Information Engineering, Beijing","China School of Cyber Security, University of Chinese Academy of Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Information Engineering,Beijing","institution_ids":["https://openalex.org/I4210156404"]},{"raw_affiliation_string":"Institute of Information Engineering, Beijing","institution_ids":["https://openalex.org/I4210156404"]},{"raw_affiliation_string":"China School of Cyber Security, University of Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100634906","display_name":"Chuang Zhang","orcid":"https://orcid.org/0000-0001-6685-7048"},"institutions":[{"id":"https://openalex.org/I4210156404","display_name":"Institute of Information Engineering","ror":"https://ror.org/04r53se39","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chuang Zhang","raw_affiliation_strings":["Institute of Information Engineering,Beijing","Institute of Information Engineering, Beijing"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Information Engineering,Beijing","institution_ids":["https://openalex.org/I4210156404"]},{"raw_affiliation_string":"Institute of Information Engineering, Beijing","institution_ids":["https://openalex.org/I4210156404"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100412721","display_name":"Xiaojun Liu","orcid":"https://orcid.org/0000-0003-3399-3486"},"institutions":[{"id":"https://openalex.org/I4210156404","display_name":"Institute of Information Engineering","ror":"https://ror.org/04r53se39","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaojun Liu","raw_affiliation_strings":["Institute of Information Engineering,Beijing","China School of Cyber Security, University of Chinese Academy of Sciences","Institute of Information Engineering, Beijing"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Information Engineering,Beijing","institution_ids":["https://openalex.org/I4210156404"]},{"raw_affiliation_string":"China School of Cyber Security, University of Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210165038"]},{"raw_affiliation_string":"Institute of Information Engineering, Beijing","institution_ids":["https://openalex.org/I4210156404"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100369438","display_name":"Xiaojun Chen","orcid":"https://orcid.org/0000-0002-2818-4652"},"institutions":[{"id":"https://openalex.org/I4210156404","display_name":"Institute of Information Engineering","ror":"https://ror.org/04r53se39","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaojun Chen","raw_affiliation_strings":["Institute of Information Engineering,Beijing","Institute of Information Engineering, Beijing"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Information Engineering,Beijing","institution_ids":["https://openalex.org/I4210156404"]},{"raw_affiliation_string":"Institute of Information Engineering, Beijing","institution_ids":["https://openalex.org/I4210156404"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044045771","display_name":"Peng Zhang","orcid":"https://orcid.org/0000-0001-9518-5914"},"institutions":[{"id":"https://openalex.org/I4210156404","display_name":"Institute of Information Engineering","ror":"https://ror.org/04r53se39","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Peng Zhang","raw_affiliation_strings":["Institute of Information Engineering,Beijing","Institute of Information Engineering, Beijing"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Information Engineering,Beijing","institution_ids":["https://openalex.org/I4210156404"]},{"raw_affiliation_string":"Institute of Information Engineering, Beijing","institution_ids":["https://openalex.org/I4210156404"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100454211","display_name":"Jie Liu","orcid":"https://orcid.org/0000-0003-3745-7541"},"institutions":[{"id":"https://openalex.org/I4210156404","display_name":"Institute of Information Engineering","ror":"https://ror.org/04r53se39","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jie Liu","raw_affiliation_strings":["Institute of Information Engineering,Beijing","Institute of Information Engineering, Beijing"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Information Engineering,Beijing","institution_ids":["https://openalex.org/I4210156404"]},{"raw_affiliation_string":"Institute of Information Engineering, Beijing","institution_ids":["https://openalex.org/I4210156404"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"abs 1910 523","issue":null,"first_page":"2260","last_page":"2272"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":1.0,"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/T10028","display_name":"Topic Modeling","score":1.0,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9994999766349792,"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":0.9988999962806702,"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":0.9737274646759033},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8198035955429077},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.7288248538970947},{"id":"https://openalex.org/keywords/multi-document-summarization","display_name":"Multi-document summarization","score":0.6175432801246643},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.6068875789642334},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.547228991985321},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.5447065234184265},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.5219678282737732},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5003130435943604},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.4925749897956848},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.4891067147254944}],"concepts":[{"id":"https://openalex.org/C170858558","wikidata":"https://www.wikidata.org/wiki/Q1394144","display_name":"Automatic summarization","level":2,"score":0.9737274646759033},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8198035955429077},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.7288248538970947},{"id":"https://openalex.org/C134714966","wikidata":"https://www.wikidata.org/wiki/Q6934448","display_name":"Multi-document summarization","level":3,"score":0.6175432801246643},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6068875789642334},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.547228991985321},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.5447065234184265},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.5219678282737732},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5003130435943604},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.4925749897956848},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.4891067147254944},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icpr56361.2022.9956691","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icpr56361.2022.9956691","pdf_url":null,"source":{"id":"https://openalex.org/S4363607731","display_name":"2022 26th International Conference on Pattern Recognition (ICPR)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 26th International Conference on Pattern Recognition (ICPR)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6800000071525574,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":61,"referenced_works":["https://openalex.org/W9655565","https://openalex.org/W1525595230","https://openalex.org/W1587871245","https://openalex.org/W2133564696","https://openalex.org/W2138605095","https://openalex.org/W2145689431","https://openalex.org/W2150824314","https://openalex.org/W2467173223","https://openalex.org/W2508113264","https://openalex.org/W2567525733","https://openalex.org/W2606974598","https://openalex.org/W2754697883","https://openalex.org/W2790823116","https://openalex.org/W2799029897","https://openalex.org/W2808294523","https://openalex.org/W2896457183","https://openalex.org/W2897803242","https://openalex.org/W2949615363","https://openalex.org/W2950620609","https://openalex.org/W2952138241","https://openalex.org/W2953280096","https://openalex.org/W2962800143","https://openalex.org/W2962849707","https://openalex.org/W2962965405","https://openalex.org/W2962996600","https://openalex.org/W2963204221","https://openalex.org/W2963926728","https://openalex.org/W2963929190","https://openalex.org/W2970419734","https://openalex.org/W2971139875","https://openalex.org/W2972111982","https://openalex.org/W2989743967","https://openalex.org/W3034945650","https://openalex.org/W3034999214","https://openalex.org/W3035050380","https://openalex.org/W3045828162","https://openalex.org/W3091863267","https://openalex.org/W3099286868","https://openalex.org/W3100560913","https://openalex.org/W3101600240","https://openalex.org/W3114932121","https://openalex.org/W3116865665","https://openalex.org/W3158631574","https://openalex.org/W3161478719","https://openalex.org/W3173210704","https://openalex.org/W3198659451","https://openalex.org/W4292779060","https://openalex.org/W4385245566","https://openalex.org/W6600394458","https://openalex.org/W6631501603","https://openalex.org/W6632455782","https://openalex.org/W6679434410","https://openalex.org/W6681523579","https://openalex.org/W6697028822","https://openalex.org/W6725207838","https://openalex.org/W6731447273","https://openalex.org/W6739901393","https://openalex.org/W6755207826","https://openalex.org/W6778883912","https://openalex.org/W6787916745","https://openalex.org/W6891932496"],"related_works":["https://openalex.org/W3164984162","https://openalex.org/W2104677027","https://openalex.org/W2902627734","https://openalex.org/W2112885393","https://openalex.org/W2173208124","https://openalex.org/W2568827738","https://openalex.org/W1990695371","https://openalex.org/W2365100044","https://openalex.org/W2099859325","https://openalex.org/W2474342320"],"abstract_inverted_index":{"Recently,":[0],"the":[1,16,19,30,36,49,82,129,137,145,150,155,158,163,168,178],"field":[2],"of":[3,32,51,124,167,180],"natural":[4],"language":[5],"processing":[6],"(NLP)":[7],"has":[8,25],"grown":[9],"rapidly,":[10],"driven":[11],"by":[12,118],"massive":[13],"datasets.":[14],"At":[15],"same":[17],"time,":[18],"need":[20],"for":[21,45,61,171],"automatic":[22,65,172],"summarization":[23,106,174],"systems":[24],"been":[26],"rapidly":[27],"increasing":[28],"as":[29],"amount":[31],"textual":[33],"information":[34],"on":[35,64],"web":[37],"and":[38,53,75,80,85,91,115,140,165],"in":[39],"large":[40],"data":[41],"centers":[42],"became":[43],"intractable":[44],"human":[46],"readers.":[47],"However,":[48],"lack":[50],"large-scale":[52,102],"high-quality":[54],"Chinese":[55,77,103,112],"datasets":[56],"remain":[57],"a":[58,101],"critical":[59],"bottleneck":[60],"further":[62],"research":[63],"text":[66,173],"summarization.":[67],"To":[68],"close":[69],"this":[70],"gap,":[71],"we":[72],"searched":[73],"domestic":[74],"foreign":[76],"news":[78,105,114],"websites":[79],"designed":[81,141],"FCFS":[83],"(Format":[84],"Content":[86],"Filtering":[87],"System)":[88],"to":[89,95,128,148],"crawl":[90],"filter":[92],"these":[93],"records":[94],"construct":[96],"NEWSFARM.":[97],"The":[98],"NEWSFARM":[99],"is":[100],"long":[104,113],"corpus,":[107],"containing":[108],"more":[109],"than":[110],"220K":[111],"summaries":[116],"written":[117],"professional":[119],"editors":[120],"or":[121],"authors,":[122],"all":[123],"which":[125],"are":[126],"released":[127],"public":[130],"<sup":[131],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[132],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup>":[133],".":[134],"We":[135],"calculated":[136],"static":[138],"metrics":[139],"many":[142],"experiments":[143],"with":[144,154],"baseline":[146],"models":[147],"evaluate":[149],"dataset.":[151],"By":[152],"comparing":[153],"common":[156],"datasets,":[157],"results":[159],"not":[160],"only":[161],"demonstrate":[162],"usefulness":[164],"challenges":[166],"proposed":[169],"corpus":[170],"but":[175],"also":[176],"validate":[177],"superiority":[179],"FCFS.":[181]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}