{"id":"https://openalex.org/W3161478719","doi":"https://doi.org/10.1109/icassp39728.2021.9414946","title":"A Large-Scale Chinese Long-Text Extractive Summarization Corpus","display_name":"A Large-Scale Chinese Long-Text Extractive Summarization Corpus","publication_year":2021,"publication_date":"2021-05-13","ids":{"openalex":"https://openalex.org/W3161478719","doi":"https://doi.org/10.1109/icassp39728.2021.9414946","mag":"3161478719"},"language":"en","primary_location":{"id":"doi:10.1109/icassp39728.2021.9414946","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414946","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5100438001","display_name":"Kai Chen","orcid":"https://orcid.org/0000-0003-2587-6028"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]},{"id":"https://openalex.org/I4210144487","display_name":"Cloud Computing Center","ror":"https://ror.org/04aa0zm65","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210144487"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kai Chen","raw_affiliation_strings":["Intelligent Computing Research Center, Harbin Institute of Technology (Shenzhen)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Intelligent Computing Research Center, Harbin Institute of Technology (Shenzhen)","institution_ids":["https://openalex.org/I4210144487","https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006438734","display_name":"Guanyu Fu","orcid":null},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]},{"id":"https://openalex.org/I4210144487","display_name":"Cloud Computing Center","ror":"https://ror.org/04aa0zm65","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210144487"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guanyu Fu","raw_affiliation_strings":["Intelligent Computing Research Center, Harbin Institute of Technology (Shenzhen)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Intelligent Computing Research Center, Harbin Institute of Technology (Shenzhen)","institution_ids":["https://openalex.org/I4210144487","https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101895423","display_name":"Qingcai Chen","orcid":"https://orcid.org/0000-0001-8473-7293"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]},{"id":"https://openalex.org/I4210144487","display_name":"Cloud Computing Center","ror":"https://ror.org/04aa0zm65","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210144487"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qingcai Chen","raw_affiliation_strings":["Intelligent Computing Research Center, Harbin Institute of Technology (Shenzhen)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Intelligent Computing Research Center, Harbin Institute of Technology (Shenzhen)","institution_ids":["https://openalex.org/I4210144487","https://openalex.org/I204983213"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5083079672","display_name":"Baotian Hu","orcid":"https://orcid.org/0000-0001-7490-684X"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]},{"id":"https://openalex.org/I4210144487","display_name":"Cloud Computing Center","ror":"https://ror.org/04aa0zm65","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210144487"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Baotian Hu","raw_affiliation_strings":["Intelligent Computing Research Center, Harbin Institute of Technology (Shenzhen)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Intelligent Computing Research Center, Harbin Institute of Technology (Shenzhen)","institution_ids":["https://openalex.org/I4210144487","https://openalex.org/I204983213"]}]}],"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":4,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"7828","last_page":"7832"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","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/T10028","display_name":"Topic Modeling","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/T10181","display_name":"Natural Language Processing Techniques","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":0.9912999868392944,"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":0.9684349298477173},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.7677100896835327},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7455899715423584},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6638160347938538},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.6515025496482849},{"id":"https://openalex.org/keywords/relevance","display_name":"Relevance (law)","score":0.6020259261131287},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5508428812026978},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5038427710533142},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.5013942718505859},{"id":"https://openalex.org/keywords/text-corpus","display_name":"Text corpus","score":0.42074066400527954}],"concepts":[{"id":"https://openalex.org/C170858558","wikidata":"https://www.wikidata.org/wiki/Q1394144","display_name":"Automatic summarization","level":2,"score":0.9684349298477173},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.7677100896835327},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7455899715423584},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6638160347938538},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.6515025496482849},{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.6020259261131287},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5508428812026978},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5038427710533142},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.5013942718505859},{"id":"https://openalex.org/C2474386","wikidata":"https://www.wikidata.org/wiki/Q461183","display_name":"Text corpus","level":2,"score":0.42074066400527954},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","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/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp39728.2021.9414946","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414946","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.8299999833106995,"display_name":"Quality Education"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321940","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W1544827683","https://openalex.org/W2118434577","https://openalex.org/W2119717200","https://openalex.org/W2154652894","https://openalex.org/W2170738476","https://openalex.org/W2173487081","https://openalex.org/W2307381258","https://openalex.org/W2386010330","https://openalex.org/W2574535369","https://openalex.org/W2757311323","https://openalex.org/W2800233718","https://openalex.org/W2896457183","https://openalex.org/W2923014074","https://openalex.org/W2924690340","https://openalex.org/W2949615363","https://openalex.org/W2951359136","https://openalex.org/W2952138241","https://openalex.org/W2953094427","https://openalex.org/W2962762898","https://openalex.org/W2962972512","https://openalex.org/W2962996600","https://openalex.org/W2963310665","https://openalex.org/W2963341956","https://openalex.org/W2963403868","https://openalex.org/W2963545005","https://openalex.org/W2963929190","https://openalex.org/W2964259363","https://openalex.org/W3035446106","https://openalex.org/W3158986179","https://openalex.org/W4385245566","https://openalex.org/W6632455782","https://openalex.org/W6677566513","https://openalex.org/W6682631176","https://openalex.org/W6685160515","https://openalex.org/W6711000320","https://openalex.org/W6739901393","https://openalex.org/W6750936306","https://openalex.org/W6755207826","https://openalex.org/W6761268247","https://openalex.org/W6795224213"],"related_works":["https://openalex.org/W2366403280","https://openalex.org/W1495108544","https://openalex.org/W2091301346","https://openalex.org/W3148229873","https://openalex.org/W4389760904","https://openalex.org/W2150160875","https://openalex.org/W4242223894","https://openalex.org/W4306886878","https://openalex.org/W1517524280","https://openalex.org/W2740913191"],"abstract_inverted_index":{"Recently,":[0],"large-scale":[1,40],"datasets":[2],"have":[3],"vastly":[4],"facilitated":[5],"the":[6,69,72,78,90,117],"development":[7],"in":[8],"nearly":[9],"domains":[10],"of":[11,71,81],"Natural":[12],"Language":[13],"Processing.":[14],"However,":[15],"lacking":[16],"large":[17],"scale":[18],"Chinese":[19,41],"corpus":[20,45,92,123],"is":[21,57],"still":[22],"a":[23,39],"critical":[24],"bottleneck":[25],"for":[26,124],"further":[27,114,125],"research":[28,115,126],"on":[29,89,116],"deep":[30,95],"text":[31],"summarization":[32],"methods.":[33],"In":[34],"this":[35,122],"paper,":[36],"we":[37,74],"publish":[38],"Long-text":[42],"Extractive":[43],"Summarization":[44],"named":[46],"CLES.":[47],"The":[48],"CLES":[49],"contains":[50],"about":[51],"104K":[52],"<summary,":[53,83],"article>":[54,84],"pairs,":[55],"which":[56],"originally":[58],"collected":[59],"from":[60],"Sina":[61],"Weibo":[62],"<sup":[63,127],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[64,128],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup>":[65],".":[66,130],"To":[67],"verify":[68],"quality":[70],"corpus,":[73],"also":[75],"manually":[76],"tagged":[77],"relevance":[79],"score":[80],"5,000":[82],"pairs.":[85],"Our":[86],"benchmark":[87],"models":[88,99],"proposed":[91],"include":[93],"conventional":[94],"learning":[96],"based":[97],"extractive":[98],"and":[100,109],"several":[101],"pre-trained":[102],"Bert-based":[103],"algorithms.":[104],"Their":[105],"performances":[106],"are":[107],"reported":[108],"briefly":[110],"analyzed":[111],"to":[112],"facilitate":[113],"corpus.":[118],"We":[119],"will":[120],"release":[121],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">2</sup>":[129]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}