{"id":"https://openalex.org/W3210563124","doi":"https://doi.org/10.1145/3459637.3482121","title":"How to Leverage a Multi-layered Transformer Language Model for Text Clustering","display_name":"How to Leverage a Multi-layered Transformer Language Model for Text Clustering","publication_year":2021,"publication_date":"2021-10-26","ids":{"openalex":"https://openalex.org/W3210563124","doi":"https://doi.org/10.1145/3459637.3482121","mag":"3210563124"},"language":"en","primary_location":{"id":"doi:10.1145/3459637.3482121","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3459637.3482121","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM International Conference on Information & Knowledge Management","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/A5032827743","display_name":"Mira Ait-Saada","orcid":null},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I204730241","display_name":"Universit\u00e9 Paris Cit\u00e9","ror":"https://ror.org/05f82e368","country_code":"FR","type":"education","lineage":["https://openalex.org/I204730241"]},{"id":"https://openalex.org/I4403386768","display_name":"Centre Borelli","ror":"https://ror.org/02hcn4061","country_code":"FR","type":"facility","lineage":["https://openalex.org/I11559806","https://openalex.org/I1294671590","https://openalex.org/I204730241","https://openalex.org/I277688954","https://openalex.org/I4210129973","https://openalex.org/I4210136310","https://openalex.org/I4403386768"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Mira Ait-Saada","raw_affiliation_strings":["Universit\u00e9 de Paris CNRS, Centre Borelli UMR 9010 & Groupe Caisse des D\u00e9p\u00f4ts, Paris, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universit\u00e9 de Paris CNRS, Centre Borelli UMR 9010 & Groupe Caisse des D\u00e9p\u00f4ts, Paris, France","institution_ids":["https://openalex.org/I1294671590","https://openalex.org/I204730241","https://openalex.org/I4403386768"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003511531","display_name":"Fran\u00e7ois Role","orcid":null},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I204730241","display_name":"Universit\u00e9 Paris Cit\u00e9","ror":"https://ror.org/05f82e368","country_code":"FR","type":"education","lineage":["https://openalex.org/I204730241"]},{"id":"https://openalex.org/I4403386768","display_name":"Centre Borelli","ror":"https://ror.org/02hcn4061","country_code":"FR","type":"facility","lineage":["https://openalex.org/I11559806","https://openalex.org/I1294671590","https://openalex.org/I204730241","https://openalex.org/I277688954","https://openalex.org/I4210129973","https://openalex.org/I4210136310","https://openalex.org/I4403386768"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Fran\u00e7ois Role","raw_affiliation_strings":["Universit\u00e9 de Paris, CNRS, Centre Borelli UMR 9010, Paris, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universit\u00e9 de Paris, CNRS, Centre Borelli UMR 9010, Paris, France","institution_ids":["https://openalex.org/I1294671590","https://openalex.org/I204730241","https://openalex.org/I4403386768"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5007054746","display_name":"Mohamed Nadif","orcid":"https://orcid.org/0000-0002-0007-3950"},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I204730241","display_name":"Universit\u00e9 Paris Cit\u00e9","ror":"https://ror.org/05f82e368","country_code":"FR","type":"education","lineage":["https://openalex.org/I204730241"]},{"id":"https://openalex.org/I4403386768","display_name":"Centre Borelli","ror":"https://ror.org/02hcn4061","country_code":"FR","type":"facility","lineage":["https://openalex.org/I11559806","https://openalex.org/I1294671590","https://openalex.org/I204730241","https://openalex.org/I277688954","https://openalex.org/I4210129973","https://openalex.org/I4210136310","https://openalex.org/I4403386768"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Mohamed Nadif","raw_affiliation_strings":["Universit\u00e9 de Paris, CNRS, Centre Borelli UMR 9010, Paris, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universit\u00e9 de Paris, CNRS, Centre Borelli UMR 9010, Paris, France","institution_ids":["https://openalex.org/I1294671590","https://openalex.org/I204730241","https://openalex.org/I4403386768"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.7326,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.73940665,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"2837","last_page":"2841"},"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9993000030517578,"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":0.9983999729156494,"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":0.7730106115341187},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.770026683807373},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.7218414545059204},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.636025071144104},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5484106540679932},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5313411951065063},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4235178828239441},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4126240015029907},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3423507809638977},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.108721524477005}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7730106115341187},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.770026683807373},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.7218414545059204},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.636025071144104},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5484106540679932},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5313411951065063},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4235178828239441},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4126240015029907},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3423507809638977},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.108721524477005},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3459637.3482121","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3459637.3482121","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM International Conference on Information & Knowledge Management","raw_type":"proceedings-article"},{"id":"pmh:oai:HAL:hal-03963423v1","is_oa":false,"landing_page_url":"https://hal.science/hal-03963423","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"CIKM '21: The 30th ACM International Conference on Information and Knowledge Management, Nov 2021, Queensland Australia, Australia. pp.2837-2841, ⟨10.1145/3459637.3482121⟩","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.75,"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":22,"referenced_works":["https://openalex.org/W1944329887","https://openalex.org/W1983099884","https://openalex.org/W2002767255","https://openalex.org/W2097645701","https://openalex.org/W2129250947","https://openalex.org/W2131681506","https://openalex.org/W2294906672","https://openalex.org/W2299467264","https://openalex.org/W2538920018","https://openalex.org/W2888329843","https://openalex.org/W2892181857","https://openalex.org/W2946417913","https://openalex.org/W2970172244","https://openalex.org/W3040359118","https://openalex.org/W3093889362","https://openalex.org/W3099178230","https://openalex.org/W3099768174","https://openalex.org/W3106209931","https://openalex.org/W4235169531","https://openalex.org/W4239019441","https://openalex.org/W4288086191","https://openalex.org/W7015365012"],"related_works":["https://openalex.org/W3049463507","https://openalex.org/W2936497627","https://openalex.org/W4288365749","https://openalex.org/W3013624417","https://openalex.org/W4287826556","https://openalex.org/W4287598411","https://openalex.org/W3098382480","https://openalex.org/W3198458223","https://openalex.org/W4288267738","https://openalex.org/W3126642501"],"abstract_inverted_index":{"Pre-trained":[0],"Transformer-based":[1],"word":[2],"embeddings":[3,37,59],"are":[4,13],"now":[5],"widely":[6],"used":[7],"in":[8,82],"text":[9,22,101],"mining":[10],"where":[11],"they":[12],"known":[14],"to":[15,54,63,136],"significantly":[16],"improve":[17],"supervised":[18],"tasks":[19],"such":[20],"as":[21],"classification,":[23],"named":[24],"entity":[25],"recognition":[26],"and":[27],"question":[28],"answering.":[29],"Since":[30],"the":[31,39,64,67,72,83,91,97,114,129,132],"Transformer":[32,94,126],"models":[33,95,127],"create":[34],"several":[35,137],"different":[36,125],"for":[38],"same":[40,73],"input,":[41],"one":[42],"at":[43],"each":[44],"layer":[45],"of":[46,57,66,93,100,131],"their":[47],"architecture,":[48],"various":[49],"studies":[50],"have":[51],"already":[52],"tried":[53],"identify":[55],"those":[56],"these":[58],"that":[60,111],"most":[61],"contribute":[62],"success":[65],"above-mentioned":[68],"tasks.":[69],"In":[70,86,103],"contrast":[71],"performance":[74],"analysis":[75],"has":[76],"not":[77],"yet":[78],"been":[79],"carried":[80,119],"out":[81,120],"unsupervised":[84],"setting.":[85],"this":[87],"paper":[88],"we":[89,105],"evaluate":[90],"effectiveness":[92,130],"on":[96,121],"important":[98],"task":[99],"clustering.":[102],"particular,":[104],"present":[106],"a":[107],"clustering":[108],"ensemble":[109],"approach":[110],"harnesses":[112],"all":[113],"network's":[115],"layers.":[116],"Numerical":[117],"experiments":[118],"real":[122],"datasets":[123],"with":[124],"show":[128],"proposed":[133],"method":[134],"compared":[135],"baselines.":[138]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2021-11-08T00:00:00"}