{"id":"https://openalex.org/W3037422790","doi":"https://doi.org/10.1145/3394486.3403368","title":"Taming Pretrained Transformers for Extreme Multi-label Text Classification","display_name":"Taming Pretrained Transformers for Extreme Multi-label Text Classification","publication_year":2020,"publication_date":"2020-08-20","ids":{"openalex":"https://openalex.org/W3037422790","doi":"https://doi.org/10.1145/3394486.3403368","mag":"3037422790"},"language":"en","primary_location":{"id":"doi:10.1145/3394486.3403368","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3394486.3403368","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining","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/A5006559148","display_name":"Wei-Cheng Chang","orcid":"https://orcid.org/0000-0002-5646-9356"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wei-Cheng Chang","raw_affiliation_strings":["Carnegie Mellon University, Pittsburgh, PA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023183059","display_name":"Hsiang\u2010Fu Yu","orcid":"https://orcid.org/0000-0001-5235-2962"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hsiang-Fu Yu","raw_affiliation_strings":["Amazon, Palo Alto, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon, Palo Alto, CA, USA","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017721496","display_name":"Kai Zhong","orcid":"https://orcid.org/0000-0002-9993-6954"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kai Zhong","raw_affiliation_strings":["Amazon, Palo Alto, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon, Palo Alto, CA, USA","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5106542734","display_name":"Yiming Yang","orcid":"https://orcid.org/0009-0006-3569-0023"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yiming Yang","raw_affiliation_strings":["Carnegie Mellon University, Pittsburgh, PA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5063459703","display_name":"Inderjit S. Dhillon","orcid":"https://orcid.org/0000-0002-2759-1416"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]},{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Inderjit S. Dhillon","raw_affiliation_strings":["Amazon and University of Texas at Austin, Berkeley, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon and University of Texas at Austin, Berkeley, CA, USA","institution_ids":["https://openalex.org/I1311688040","https://openalex.org/I86519309"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":205,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3163","last_page":"3171"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","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"}},"topics":[{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","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/T10028","display_name":"Topic Modeling","score":0.9991000294685364,"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":0.9966999888420105,"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":0.738564670085907},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.7174789309501648},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6434038877487183},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6020017266273499},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.581027090549469},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4250728487968445},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.35778796672821045},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3392634689807892},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.11318126320838928},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.07896167039871216},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.06914687156677246}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.738564670085907},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.7174789309501648},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6434038877487183},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6020017266273499},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.581027090549469},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4250728487968445},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.35778796672821045},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3392634689807892},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.11318126320838928},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.07896167039871216},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.06914687156677246},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3394486.3403368","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3394486.3403368","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W97540112","https://openalex.org/W2068074736","https://openalex.org/W2153579005","https://openalex.org/W2183087644","https://openalex.org/W2362855512","https://openalex.org/W2520348554","https://openalex.org/W2626778328","https://openalex.org/W2739996966","https://openalex.org/W2743021690","https://openalex.org/W2744136723","https://openalex.org/W2788125153","https://openalex.org/W2896214533","https://openalex.org/W2906963924","https://openalex.org/W2950352656","https://openalex.org/W2950813464","https://openalex.org/W2951434086","https://openalex.org/W2962739339","https://openalex.org/W2970574105"],"related_works":["https://openalex.org/W2389214306","https://openalex.org/W2965083567","https://openalex.org/W4235240664","https://openalex.org/W1838576100","https://openalex.org/W2757182831","https://openalex.org/W2095886385","https://openalex.org/W2375873920","https://openalex.org/W2089704382","https://openalex.org/W1983399550","https://openalex.org/W97075385"],"abstract_inverted_index":{"We":[0,168],"consider":[1],"the":[2,14,25,36,50,81,90,95,105,115,141],"extreme":[3],"multi-label":[4],"text":[5,27],"classification":[6],"(XMC)":[7],"problem:":[8],"given":[9],"an":[10,44],"input":[11,26],"text,":[12],"return":[13],"most":[15],"relevant":[16],"labels":[17,37],"from":[18,176],"a":[19,30,133,148,173],"large":[20,91],"label":[21,72,96],"collection.":[22],"For":[23],"example,":[24],"could":[28,38],"be":[29,39],"product":[31,40],"description":[32],"on":[33,62,125,132,183],"Amazon.com":[34],"and":[35,94,157,163,178],"categories.":[41],"XMC":[42,82,116,127,153],"is":[43,146],"important":[45],"yet":[46],"challenging":[47],"problem":[48,83],"in":[49],"NLP":[51,64],"community.":[52],"Recently,":[53],"deep":[54,77,111],"pretrained":[55],"transformer":[56,78,112],"models":[57,79,113],"have":[58],"achieved":[59],"state-of-the-art":[60,123,152],"performance":[61,87],"many":[63],"tasks":[65],"including":[66],"sentence":[67],"classification,":[68],"albeit":[69],"with":[70,136],"small":[71],"sets.":[73],"However,":[74],"naively":[75],"applying":[76],"to":[80,85,89,109,172],"leads":[84],"sub-optimal":[86],"due":[88],"output":[92],"space":[93],"sparsity":[97],"issue.":[98],"In":[99,130],"this":[100],"paper,":[101],"we":[102],"propose":[103],"X-Transformer,":[104],"first":[106],"scalable":[107],"approach":[108],"fine-tuning":[110],"for":[114],"problem.":[117],"The":[118],"proposed":[119],"method":[120],"achieves":[121],"new":[122],"results":[124],"four":[126],"benchmark":[128],"datasets.":[129],"particular,":[131],"Wiki":[134],"dataset":[135,175],"around":[137],"0.5":[138],"million":[139],"labels,":[140],"[email":[142,165,184],"protected]":[143,185],"of":[144],"X-Transformer":[145,171],"77.28%,":[147],"substantial":[149],"improvement":[150,182],"over":[151,186],"approaches":[154],"Parabel":[155],"(linear)":[156],"AttentionXML":[158],"(neural),":[159],"which":[160],"achieve":[161],"68.70%":[162],"76.95%":[164],"protected],":[166],"respectively.":[167],"further":[169],"apply":[170],"product2query":[174],"Amazon":[177],"gained":[179],"10.7%":[180],"relative":[181],"Parabel.":[187]},"counts_by_year":[{"year":2026,"cited_by_count":6},{"year":2025,"cited_by_count":22},{"year":2024,"cited_by_count":31},{"year":2023,"cited_by_count":44},{"year":2022,"cited_by_count":45},{"year":2021,"cited_by_count":53},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":1}],"updated_date":"2026-07-23T08:03:31.855105","created_date":"2025-10-10T00:00:00"}