{"id":"https://openalex.org/W4366850523","doi":"https://doi.org/10.1145/3543507.3583457","title":"CEIL: A General Classification-Enhanced Iterative Learning Framework for Text Clustering","display_name":"CEIL: A General Classification-Enhanced Iterative Learning Framework for Text Clustering","publication_year":2023,"publication_date":"2023-04-26","ids":{"openalex":"https://openalex.org/W4366850523","doi":"https://doi.org/10.1145/3543507.3583457"},"language":"en","primary_location":{"id":"doi:10.1145/3543507.3583457","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3543507.3583457","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 Web Conference 2023","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2304.11061","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5103834539","display_name":"Mingjun Zhao","orcid":"https://orcid.org/0000-0003-0405-7154"},"institutions":[{"id":"https://openalex.org/I154425047","display_name":"University of Alberta","ror":"https://ror.org/0160cpw27","country_code":"CA","type":"education","lineage":["https://openalex.org/I154425047"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Mingjun Zhao","raw_affiliation_strings":["Electrical & Computer Engineering, University of Alberta, Canada"],"affiliations":[{"raw_affiliation_string":"Electrical & Computer Engineering, University of Alberta, Canada","institution_ids":["https://openalex.org/I154425047"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051810784","display_name":"Mengzhen Wang","orcid":"https://orcid.org/0000-0002-4086-2743"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mengzhen Wang","raw_affiliation_strings":["DiDi Global, China"],"affiliations":[{"raw_affiliation_string":"DiDi Global, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076116273","display_name":"Yinglong Ma","orcid":"https://orcid.org/0000-0003-4732-4865"},"institutions":[{"id":"https://openalex.org/I153473198","display_name":"North China Electric Power University","ror":"https://ror.org/04qr5t414","country_code":"CN","type":"education","lineage":["https://openalex.org/I153473198"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yinglong Ma","raw_affiliation_strings":["North China Electric Power University, China"],"affiliations":[{"raw_affiliation_string":"North China Electric Power University, China","institution_ids":["https://openalex.org/I153473198"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032424832","display_name":"Di Niu","orcid":"https://orcid.org/0000-0002-5250-7327"},"institutions":[{"id":"https://openalex.org/I154425047","display_name":"University of Alberta","ror":"https://ror.org/0160cpw27","country_code":"CA","type":"education","lineage":["https://openalex.org/I154425047"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Di Niu","raw_affiliation_strings":["Electrical & Computer Engineering, University of Alberta, Canada"],"affiliations":[{"raw_affiliation_string":"Electrical & Computer Engineering, University of Alberta, Canada","institution_ids":["https://openalex.org/I154425047"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5063102955","display_name":"Haijiang Wu","orcid":"https://orcid.org/0000-0002-7304-7059"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Haijiang Wu","raw_affiliation_strings":["DiDi Global, China"],"affiliations":[{"raw_affiliation_string":"DiDi Global, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5103834539"],"corresponding_institution_ids":["https://openalex.org/I154425047"],"apc_list":null,"apc_paid":null,"fwci":0.3554,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.63797137,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1784","last_page":"1792"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9994000196456909,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9994000196456909,"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":0.9987000226974487,"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":0.9972000122070312,"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/cluster-analysis","display_name":"Cluster analysis","score":0.9234668016433716},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.774088442325592},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6272863149642944},{"id":"https://openalex.org/keywords/conceptual-clustering","display_name":"Conceptual clustering","score":0.6127256751060486},{"id":"https://openalex.org/keywords/document-clustering","display_name":"Document clustering","score":0.5378486514091492},{"id":"https://openalex.org/keywords/correlation-clustering","display_name":"Correlation clustering","score":0.5340420603752136},{"id":"https://openalex.org/keywords/canopy-clustering-algorithm","display_name":"Canopy clustering algorithm","score":0.5016074180603027},{"id":"https://openalex.org/keywords/cure-data-clustering-algorithm","display_name":"CURE data clustering algorithm","score":0.46653348207473755},{"id":"https://openalex.org/keywords/brown-clustering","display_name":"Brown clustering","score":0.4556877315044403},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4522838592529297},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.43730270862579346},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.4108964204788208},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3765835165977478},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3676908016204834}],"concepts":[{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.9234668016433716},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.774088442325592},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6272863149642944},{"id":"https://openalex.org/C39235581","wikidata":"https://www.wikidata.org/wiki/Q5158434","display_name":"Conceptual clustering","level":5,"score":0.6127256751060486},{"id":"https://openalex.org/C177937566","wikidata":"https://www.wikidata.org/wiki/Q4223102","display_name":"Document clustering","level":3,"score":0.5378486514091492},{"id":"https://openalex.org/C94641424","wikidata":"https://www.wikidata.org/wiki/Q5172845","display_name":"Correlation clustering","level":3,"score":0.5340420603752136},{"id":"https://openalex.org/C104047586","wikidata":"https://www.wikidata.org/wiki/Q5033439","display_name":"Canopy clustering algorithm","level":4,"score":0.5016074180603027},{"id":"https://openalex.org/C33704608","wikidata":"https://www.wikidata.org/wiki/Q5014717","display_name":"CURE data clustering algorithm","level":4,"score":0.46653348207473755},{"id":"https://openalex.org/C167984511","wikidata":"https://www.wikidata.org/wiki/Q17003931","display_name":"Brown clustering","level":5,"score":0.4556877315044403},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4522838592529297},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.43730270862579346},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.4108964204788208},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3765835165977478},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3676908016204834},{"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/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3543507.3583457","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3543507.3583457","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 Web Conference 2023","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2304.11061","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2304.11061","pdf_url":"https://arxiv.org/pdf/2304.11061","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2304.11061","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2304.11061","pdf_url":"https://arxiv.org/pdf/2304.11061","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4366850523.pdf","grobid_xml":"https://content.openalex.org/works/W4366850523.grobid-xml"},"referenced_works_count":29,"referenced_works":["https://openalex.org/W1775434803","https://openalex.org/W1970544520","https://openalex.org/W1984270672","https://openalex.org/W1987938583","https://openalex.org/W2058990119","https://openalex.org/W2083778364","https://openalex.org/W2088314245","https://openalex.org/W2171836785","https://openalex.org/W2187089797","https://openalex.org/W2250539671","https://openalex.org/W2442340835","https://openalex.org/W2462891382","https://openalex.org/W2533545350","https://openalex.org/W2576754561","https://openalex.org/W2798991696","https://openalex.org/W2893667345","https://openalex.org/W2896457183","https://openalex.org/W2899771611","https://openalex.org/W2962852342","https://openalex.org/W2964074409","https://openalex.org/W2969521304","https://openalex.org/W2970641574","https://openalex.org/W3005680577","https://openalex.org/W3035524453","https://openalex.org/W3035983125","https://openalex.org/W3171153522","https://openalex.org/W4283813539","https://openalex.org/W4294170691","https://openalex.org/W4309444617"],"related_works":["https://openalex.org/W2385630304","https://openalex.org/W2160785859","https://openalex.org/W2622412490","https://openalex.org/W2353797829","https://openalex.org/W2087424554","https://openalex.org/W1957537378","https://openalex.org/W3161536855","https://openalex.org/W3140018618","https://openalex.org/W2607137685","https://openalex.org/W2049890817"],"abstract_inverted_index":{"Text":[0],"clustering,":[1,88],"as":[2,154],"one":[3],"of":[4,28,227],"the":[5,25,42,62,94,118,124,159,163,172,186,193,198,219],"most":[6,44,63],"fundamental":[7],"challenges":[8],"in":[9,55,68,185],"unsupervised":[10],"learning,":[11,30],"aims":[12,90],"at":[13,91],"grouping":[14],"semantically":[15],"similar":[16],"text":[17,47,87,120,229],"segments":[18],"without":[19],"relying":[20],"on":[21,52,207,215,223],"human":[22],"annotations.":[23],"With":[24],"rapid":[26],"development":[27],"deep":[29,31,46],"clustering":[32,39,48,67,95,125,184,199,209,221,230],"has":[33],"achieved":[34],"significant":[35],"advantages":[36],"over":[37,201],"traditional":[38],"methods.":[40,236],"Despite":[41],"effectiveness,":[43],"existing":[45],"methods":[49],"rely":[50],"heavily":[51],"representations":[53],"pre-trained":[54],"general":[56],"domains,":[57],"which":[58,89,123,152],"may":[59],"not":[60],"be":[61],"suitable":[64],"solution":[65],"for":[66,85],"specific":[69],"target":[70],"domains.":[71],"To":[72],"address":[73],"this":[74],"issue,":[75],"we":[76,110,217],"propose":[77],"CEIL,":[78],"a":[79,99,113,167,224],"novel":[80],"Classification-Enhanced":[81],"Iterative":[82],"Learning":[83],"framework":[84,195],"short":[86,228],"generally":[92,205],"promoting":[93],"performance":[96,200,222],"by":[97,212],"introducing":[98],"classification":[100,164],"objective":[101,165],"to":[102,116,157,182],"iteratively":[103],"improve":[104],"feature":[105],"representations.":[106],"In":[107],"each":[108],"iteration,":[109],"first":[111],"adopt":[112],"language":[114,160,174],"model":[115,161,175],"retrieve":[117],"initial":[119],"representations,":[121],"from":[122],"results":[126],"are":[127,150],"collected":[128],"using":[129],"our":[130],"proposed":[131],"Category":[132],"Disentangled":[133],"Contrastive":[134],"Clustering":[135],"(CDCC)":[136],"algorithm.":[137],"After":[138],"strict":[139],"data":[140],"filtering":[141],"and":[142,203],"aggregation":[143],"processes,":[144],"samples":[145],"with":[146,162,176],"clean":[147],"category":[148],"labels":[149],"retrieved,":[151],"serve":[153],"supervision":[155],"information":[156],"update":[158],"via":[166],"prompt":[168],"learning":[169],"approach.":[170],"Finally,":[171],"updated":[173],"improved":[177],"representation":[178],"ability":[179],"is":[180,204],"used":[181],"enhance":[183],"next":[187],"iteration.":[188],"Extensive":[189],"experiments":[190],"demonstrate":[191],"that":[192],"CEIL":[194,214],"significantly":[196],"improves":[197],"iterations,":[202],"effective":[206],"various":[208],"algorithms.":[210],"Moreover,":[211],"incorporating":[213],"CDCC,":[216],"achieve":[218],"state-of-the-art":[220],"wide":[225],"range":[226],"benchmarks":[231],"outperforming":[232],"other":[233],"strong":[234],"baseline":[235]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2026-03-10T16:38:18.471706","created_date":"2025-10-10T00:00:00"}