{"id":"https://openalex.org/W4312293836","doi":"https://doi.org/10.1109/icpr56361.2022.9956208","title":"Shuffle & Divide: Contrastive Learning for Long Text","display_name":"Shuffle & Divide: Contrastive Learning for Long Text","publication_year":2022,"publication_date":"2022-08-21","ids":{"openalex":"https://openalex.org/W4312293836","doi":"https://doi.org/10.1109/icpr56361.2022.9956208"},"language":"en","primary_location":{"id":"doi:10.1109/icpr56361.2022.9956208","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icpr56361.2022.9956208","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":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2304.09374","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101859889","display_name":"Joonseok Lee","orcid":"https://orcid.org/0000-0002-0786-8086"},"institutions":[{"id":"https://openalex.org/I2250650973","display_name":"Samsung (South Korea)","ror":"https://ror.org/04w3jy968","country_code":"KR","type":"company","lineage":["https://openalex.org/I2250650973"]},{"id":"https://openalex.org/I2802194831","display_name":"Samsung Medical Center","ror":"https://ror.org/05a15z872","country_code":"KR","type":"healthcare","lineage":["https://openalex.org/I2250650973","https://openalex.org/I2802194831"]},{"id":"https://openalex.org/I4387155180","display_name":"Samsung SDS (South Korea)","ror":"https://ror.org/0476bn305","country_code":null,"type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4387155180"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Joonseok Lee","raw_affiliation_strings":["Samsung SDS,Seoul,South Korea","Samsung SDS, Seoul, South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Samsung SDS,Seoul,South Korea","institution_ids":["https://openalex.org/I2250650973","https://openalex.org/I2802194831"]},{"raw_affiliation_string":"Samsung SDS, Seoul, South Korea","institution_ids":["https://openalex.org/I2250650973","https://openalex.org/I4387155180"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042704383","display_name":"Seongho Joe","orcid":null},"institutions":[{"id":"https://openalex.org/I2250650973","display_name":"Samsung (South Korea)","ror":"https://ror.org/04w3jy968","country_code":"KR","type":"company","lineage":["https://openalex.org/I2250650973"]},{"id":"https://openalex.org/I2802194831","display_name":"Samsung Medical Center","ror":"https://ror.org/05a15z872","country_code":"KR","type":"healthcare","lineage":["https://openalex.org/I2250650973","https://openalex.org/I2802194831"]},{"id":"https://openalex.org/I4387155180","display_name":"Samsung SDS (South Korea)","ror":"https://ror.org/0476bn305","country_code":null,"type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4387155180"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Seongho Joe","raw_affiliation_strings":["Samsung SDS,Seoul,South Korea","Samsung SDS, Seoul, South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Samsung SDS,Seoul,South Korea","institution_ids":["https://openalex.org/I2250650973","https://openalex.org/I2802194831"]},{"raw_affiliation_string":"Samsung SDS, Seoul, South Korea","institution_ids":["https://openalex.org/I2250650973","https://openalex.org/I4387155180"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039333241","display_name":"Kyoungwon Park","orcid":"https://orcid.org/0000-0002-1830-6839"},"institutions":[{"id":"https://openalex.org/I2250650973","display_name":"Samsung (South Korea)","ror":"https://ror.org/04w3jy968","country_code":"KR","type":"company","lineage":["https://openalex.org/I2250650973"]},{"id":"https://openalex.org/I2802194831","display_name":"Samsung Medical Center","ror":"https://ror.org/05a15z872","country_code":"KR","type":"healthcare","lineage":["https://openalex.org/I2250650973","https://openalex.org/I2802194831"]},{"id":"https://openalex.org/I4387155180","display_name":"Samsung SDS (South Korea)","ror":"https://ror.org/0476bn305","country_code":null,"type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4387155180"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Kyoungwon Park","raw_affiliation_strings":["Samsung SDS,Seoul,South Korea","Samsung SDS, Seoul, South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Samsung SDS,Seoul,South Korea","institution_ids":["https://openalex.org/I2250650973","https://openalex.org/I2802194831"]},{"raw_affiliation_string":"Samsung SDS, Seoul, South Korea","institution_ids":["https://openalex.org/I2250650973","https://openalex.org/I4387155180"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059796814","display_name":"Bogun Kim","orcid":"https://orcid.org/0000-0002-5493-1674"},"institutions":[{"id":"https://openalex.org/I2250650973","display_name":"Samsung (South Korea)","ror":"https://ror.org/04w3jy968","country_code":"KR","type":"company","lineage":["https://openalex.org/I2250650973"]},{"id":"https://openalex.org/I2802194831","display_name":"Samsung Medical Center","ror":"https://ror.org/05a15z872","country_code":"KR","type":"healthcare","lineage":["https://openalex.org/I2250650973","https://openalex.org/I2802194831"]},{"id":"https://openalex.org/I4387155180","display_name":"Samsung SDS (South Korea)","ror":"https://ror.org/0476bn305","country_code":null,"type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4387155180"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Bogun Kim","raw_affiliation_strings":["Samsung SDS,Seoul,South Korea","Samsung SDS, Seoul, South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Samsung SDS,Seoul,South Korea","institution_ids":["https://openalex.org/I2250650973","https://openalex.org/I2802194831"]},{"raw_affiliation_string":"Samsung SDS, Seoul, South Korea","institution_ids":["https://openalex.org/I2250650973","https://openalex.org/I4387155180"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011088674","display_name":"H. Kang","orcid":"https://orcid.org/0000-0001-7074-7220"},"institutions":[{"id":"https://openalex.org/I2250650973","display_name":"Samsung (South Korea)","ror":"https://ror.org/04w3jy968","country_code":"KR","type":"company","lineage":["https://openalex.org/I2250650973"]},{"id":"https://openalex.org/I2802194831","display_name":"Samsung Medical Center","ror":"https://ror.org/05a15z872","country_code":"KR","type":"healthcare","lineage":["https://openalex.org/I2250650973","https://openalex.org/I2802194831"]},{"id":"https://openalex.org/I4387155180","display_name":"Samsung SDS (South Korea)","ror":"https://ror.org/0476bn305","country_code":null,"type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4387155180"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Hoyoung Kang","raw_affiliation_strings":["Samsung SDS,Seoul,South Korea","Samsung SDS, Seoul, South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Samsung SDS,Seoul,South Korea","institution_ids":["https://openalex.org/I2250650973","https://openalex.org/I2802194831"]},{"raw_affiliation_string":"Samsung SDS, Seoul, South Korea","institution_ids":["https://openalex.org/I2250650973","https://openalex.org/I4387155180"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023381571","display_name":"Jaeseon Park","orcid":null},"institutions":[{"id":"https://openalex.org/I2250650973","display_name":"Samsung (South Korea)","ror":"https://ror.org/04w3jy968","country_code":"KR","type":"company","lineage":["https://openalex.org/I2250650973"]},{"id":"https://openalex.org/I2802194831","display_name":"Samsung Medical Center","ror":"https://ror.org/05a15z872","country_code":"KR","type":"healthcare","lineage":["https://openalex.org/I2250650973","https://openalex.org/I2802194831"]},{"id":"https://openalex.org/I4387155180","display_name":"Samsung SDS (South Korea)","ror":"https://ror.org/0476bn305","country_code":null,"type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4387155180"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jaeseon Park","raw_affiliation_strings":["Samsung SDS,Seoul,South Korea","Samsung SDS, Seoul, South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Samsung SDS,Seoul,South Korea","institution_ids":["https://openalex.org/I2250650973","https://openalex.org/I2802194831"]},{"raw_affiliation_string":"Samsung SDS, Seoul, South Korea","institution_ids":["https://openalex.org/I2250650973","https://openalex.org/I4387155180"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5012323997","display_name":"Youngjune Gwon","orcid":null},"institutions":[{"id":"https://openalex.org/I2250650973","display_name":"Samsung (South Korea)","ror":"https://ror.org/04w3jy968","country_code":"KR","type":"company","lineage":["https://openalex.org/I2250650973"]},{"id":"https://openalex.org/I2802194831","display_name":"Samsung Medical Center","ror":"https://ror.org/05a15z872","country_code":"KR","type":"healthcare","lineage":["https://openalex.org/I2250650973","https://openalex.org/I2802194831"]},{"id":"https://openalex.org/I4387155180","display_name":"Samsung SDS (South Korea)","ror":"https://ror.org/0476bn305","country_code":null,"type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4387155180"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Youngjune Gwon","raw_affiliation_strings":["Samsung SDS,Seoul,South Korea","Samsung SDS, Seoul, South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Samsung SDS,Seoul,South Korea","institution_ids":["https://openalex.org/I2250650973","https://openalex.org/I2802194831"]},{"raw_affiliation_string":"Samsung SDS, Seoul, South Korea","institution_ids":["https://openalex.org/I2250650973","https://openalex.org/I4387155180"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5101859889"],"corresponding_institution_ids":["https://openalex.org/I2250650973","https://openalex.org/I2802194831","https://openalex.org/I4387155180"],"apc_list":null,"apc_paid":null,"fwci":0.208,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.43900371,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"2935","last_page":"2941"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9991999864578247,"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":0.9991999864578247,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9991999864578247,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9987999796867371,"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/computer-science","display_name":"Computer science","score":0.845529317855835},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6563928723335266},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6459382176399231},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.5589054226875305},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.516925036907196},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4577764868736267},{"id":"https://openalex.org/keywords/word-embedding","display_name":"Word embedding","score":0.4196609854698181},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.41041100025177},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3968794345855713},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.39538607001304626}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.845529317855835},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6563928723335266},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6459382176399231},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.5589054226875305},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.516925036907196},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4577764868736267},{"id":"https://openalex.org/C2777462759","wikidata":"https://www.wikidata.org/wiki/Q18395344","display_name":"Word embedding","level":3,"score":0.4196609854698181},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.41041100025177},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3968794345855713},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.39538607001304626},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icpr56361.2022.9956208","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icpr56361.2022.9956208","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"},{"id":"pmh:oai:arXiv.org:2304.09374","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2304.09374","pdf_url":"https://arxiv.org/pdf/2304.09374","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2304.09374","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2304.09374","pdf_url":"https://arxiv.org/pdf/2304.09374","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4312293836.pdf"},"referenced_works_count":52,"referenced_works":["https://openalex.org/W343636949","https://openalex.org/W1493526108","https://openalex.org/W1790954942","https://openalex.org/W2063392856","https://openalex.org/W2150102617","https://openalex.org/W2222512263","https://openalex.org/W2321533354","https://openalex.org/W2326925005","https://openalex.org/W2739844977","https://openalex.org/W2785325870","https://openalex.org/W2887997457","https://openalex.org/W2889326796","https://openalex.org/W2896457183","https://openalex.org/W2948012107","https://openalex.org/W2952729433","https://openalex.org/W2962739339","https://openalex.org/W2964291985","https://openalex.org/W2964420626","https://openalex.org/W2970641574","https://openalex.org/W2971296908","https://openalex.org/W2996428491","https://openalex.org/W3005680577","https://openalex.org/W3034349864","https://openalex.org/W3035332461","https://openalex.org/W3035524453","https://openalex.org/W3039616371","https://openalex.org/W3110446398","https://openalex.org/W3125745296","https://openalex.org/W3183873439","https://openalex.org/W4231510805","https://openalex.org/W4287829148","https://openalex.org/W4292779060","https://openalex.org/W4297808394","https://openalex.org/W4385245566","https://openalex.org/W6635817268","https://openalex.org/W6639619044","https://openalex.org/W6681875376","https://openalex.org/W6685158001","https://openalex.org/W6700872662","https://openalex.org/W6701655646","https://openalex.org/W6739901393","https://openalex.org/W6747899497","https://openalex.org/W6754278344","https://openalex.org/W6755207826","https://openalex.org/W6763416564","https://openalex.org/W6766489549","https://openalex.org/W6768021236","https://openalex.org/W6774314701","https://openalex.org/W6774569510","https://openalex.org/W6778883912","https://openalex.org/W6790002314","https://openalex.org/W6844194202"],"related_works":["https://openalex.org/W2081900870","https://openalex.org/W2037549926","https://openalex.org/W2345479200","https://openalex.org/W2183306018","https://openalex.org/W4298130764","https://openalex.org/W2804364458","https://openalex.org/W2849310602","https://openalex.org/W3006008237","https://openalex.org/W2132641928","https://openalex.org/W4286432911"],"abstract_inverted_index":{"We":[0,111,147],"propose":[1],"a":[2,24,32,45,88],"self-supervised":[3],"learning":[4],"method":[5,18,98,116,134],"for":[6,36,161],"long":[7],"text":[8,26,94,120],"documents":[9,67],"based":[10],"on":[11,122,140,153,164],"contrastive":[12,37,78],"learning.":[13],"A":[14],"key":[15],"to":[16,39,92],"our":[17,97,115,133],"is":[19,86],"Shuffle":[20],"and":[21,80,96,128,155,167],"Divide":[22],"(SaD),":[23],"simple":[25],"augmentation":[27],"algorithm":[28],"that":[29],"sets":[30],"up":[31],"pretext":[33],"task":[34,91],"required":[35],"updates":[38],"BERT-based":[40],"document":[41,46],"embedding.":[42],"SaD":[43],"splits":[44],"into":[47],"two":[48],"sub-documents":[49,59],"containing":[50],"randomly":[51],"shuffled":[52],"words":[53],"in":[54,68,109,145],"the":[55,69,77,123,136,150,165],"entire":[56],"documents.":[57],"The":[58],"are":[60,105],"considered":[61],"positive":[62],"examples,":[63],"leaving":[64],"all":[65],"other":[66],"corpus":[70],"as":[71],"negatives.":[72],"After":[73],"SaD,":[74],"we":[75],"repeat":[76],"update":[79],"clustering":[81],"phases":[82],"until":[83],"convergence.":[84],"It":[85],"naturally":[87],"time-consuming,":[89],"cumbersome":[90],"label":[93],"documents,":[95],"can":[99],"help":[100],"alleviate":[101],"human":[102],"efforts,":[103],"which":[104],"most":[106],"expensive":[107],"resources":[108],"AI.":[110],"have":[112],"empirically":[113],"evaluated":[114],"by":[117,143],"performing":[118],"unsupervised":[119,162],"classification":[121,163],"20":[124,141],"Newsgroups,":[125],"Reuters-21578,":[126],"BBC,":[127],"BBCSport":[129,168],"datasets.":[130,169],"In":[131],"particular,":[132],"pushes":[135],"current":[137],"state-of-the-art,":[138],"SS-SB-MT,":[139],"Newsgroups":[142],"20.94%":[144],"accuracy.":[146],"also":[148],"achieve":[149],"state-of-the-art":[151],"performance":[152],"Reuters-21578":[154],"exceptionally-high":[156],"accuracy":[157],"performances":[158],"(over":[159],"95%)":[160],"BBC":[166]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2026-05-05T08:41:31.759640","created_date":"2023-01-04T00:00:00"}