{"id":"https://openalex.org/W2952230191","doi":"https://doi.org/10.18653/v1/p19-1633","title":"Hierarchical Transfer Learning for Multi-label Text Classification","display_name":"Hierarchical Transfer Learning for Multi-label Text Classification","publication_year":2019,"publication_date":"2019-01-01","ids":{"openalex":"https://openalex.org/W2952230191","doi":"https://doi.org/10.18653/v1/p19-1633","mag":"2952230191"},"language":"en","primary_location":{"id":"doi:10.18653/v1/p19-1633","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p19-1633","pdf_url":"https://www.aclweb.org/anthology/P19-1633.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/P19-1633.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5085889685","display_name":"Siddhartha Banerjee","orcid":"https://orcid.org/0000-0002-8954-4578"},"institutions":[{"id":"https://openalex.org/I4210134091","display_name":"Yahoo (United States)","ror":"https://ror.org/040dkzz12","country_code":"US","type":"company","lineage":["https://openalex.org/I4210134091"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Siddhartha Banerjee","raw_affiliation_strings":["Yahoo Research 701 First Avenue Sunnyvale, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Yahoo Research 701 First Avenue Sunnyvale, CA, USA","institution_ids":["https://openalex.org/I4210134091"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024795464","display_name":"Cem Akkaya","orcid":null},"institutions":[{"id":"https://openalex.org/I4210134091","display_name":"Yahoo (United States)","ror":"https://ror.org/040dkzz12","country_code":"US","type":"company","lineage":["https://openalex.org/I4210134091"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Cem Akkaya","raw_affiliation_strings":["Yahoo Research 701 First Avenue Sunnyvale, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Yahoo Research 701 First Avenue Sunnyvale, CA, USA","institution_ids":["https://openalex.org/I4210134091"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011818844","display_name":"Francisco Perez-Sorrosal","orcid":null},"institutions":[{"id":"https://openalex.org/I4210134091","display_name":"Yahoo (United States)","ror":"https://ror.org/040dkzz12","country_code":"US","type":"company","lineage":["https://openalex.org/I4210134091"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Francisco Perez-Sorrosal","raw_affiliation_strings":["Yahoo Research 701 First Avenue Sunnyvale, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Yahoo Research 701 First Avenue Sunnyvale, CA, USA","institution_ids":["https://openalex.org/I4210134091"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5070966667","display_name":"Kostas Tsioutsiouliklis","orcid":null},"institutions":[{"id":"https://openalex.org/I4210134091","display_name":"Yahoo (United States)","ror":"https://ror.org/040dkzz12","country_code":"US","type":"company","lineage":["https://openalex.org/I4210134091"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kostas Tsioutsiouliklis","raw_affiliation_strings":["Yahoo Research 701 First Avenue Sunnyvale, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Yahoo Research 701 First Avenue Sunnyvale, CA, USA","institution_ids":["https://openalex.org/I4210134091"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":6.6519,"has_fulltext":true,"cited_by_count":106,"citation_normalized_percentile":{"value":0.97322256,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"6295","last_page":"6300"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.9998999834060669,"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/T11550","display_name":"Text and Document Classification Technologies","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/T10028","display_name":"Topic Modeling","score":0.9969000220298767,"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":0.9871000051498413,"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":0.774966835975647},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7389911413192749},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.6601036787033081},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.5908944606781006},{"id":"https://openalex.org/keywords/binary-number","display_name":"Binary number","score":0.5640912055969238},{"id":"https://openalex.org/keywords/scratch","display_name":"Scratch","score":0.5601995587348938},{"id":"https://openalex.org/keywords/multi-label-classification","display_name":"Multi-label classification","score":0.5588389039039612},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5550633668899536},{"id":"https://openalex.org/keywords/binary-classification","display_name":"Binary classification","score":0.5490401983261108},{"id":"https://openalex.org/keywords/hierarchy","display_name":"Hierarchy","score":0.4781397581100464},{"id":"https://openalex.org/keywords/contextual-image-classification","display_name":"Contextual image classification","score":0.458895206451416},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4370138645172119},{"id":"https://openalex.org/keywords/macro","display_name":"Macro","score":0.43688690662384033},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.15690207481384277},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.10008424520492554},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09186738729476929}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.774966835975647},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7389911413192749},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.6601036787033081},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.5908944606781006},{"id":"https://openalex.org/C48372109","wikidata":"https://www.wikidata.org/wiki/Q3913","display_name":"Binary number","level":2,"score":0.5640912055969238},{"id":"https://openalex.org/C2781235140","wikidata":"https://www.wikidata.org/wiki/Q275131","display_name":"Scratch","level":2,"score":0.5601995587348938},{"id":"https://openalex.org/C2776482837","wikidata":"https://www.wikidata.org/wiki/Q3553958","display_name":"Multi-label classification","level":2,"score":0.5588389039039612},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5550633668899536},{"id":"https://openalex.org/C66905080","wikidata":"https://www.wikidata.org/wiki/Q17005494","display_name":"Binary classification","level":3,"score":0.5490401983261108},{"id":"https://openalex.org/C31170391","wikidata":"https://www.wikidata.org/wiki/Q188619","display_name":"Hierarchy","level":2,"score":0.4781397581100464},{"id":"https://openalex.org/C75294576","wikidata":"https://www.wikidata.org/wiki/Q5165192","display_name":"Contextual image classification","level":3,"score":0.458895206451416},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4370138645172119},{"id":"https://openalex.org/C166955791","wikidata":"https://www.wikidata.org/wiki/Q629579","display_name":"Macro","level":2,"score":0.43688690662384033},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.15690207481384277},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.10008424520492554},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09186738729476929},{"id":"https://openalex.org/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","level":1,"score":0.0},{"id":"https://openalex.org/C34447519","wikidata":"https://www.wikidata.org/wiki/Q179522","display_name":"Market economy","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/p19-1633","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p19-1633","pdf_url":"https://www.aclweb.org/anthology/P19-1633.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/p19-1633","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p19-1633","pdf_url":"https://www.aclweb.org/anthology/P19-1633.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.7799999713897705,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2952230191.pdf","grobid_xml":"https://content.openalex.org/works/W2952230191.grobid-xml"},"referenced_works_count":28,"referenced_works":["https://openalex.org/W1840435438","https://openalex.org/W2067594023","https://openalex.org/W2129026672","https://openalex.org/W2137165876","https://openalex.org/W2146241755","https://openalex.org/W2150102617","https://openalex.org/W2156876426","https://openalex.org/W2157331557","https://openalex.org/W2162657744","https://openalex.org/W2170738476","https://openalex.org/W2176228818","https://openalex.org/W2182822465","https://openalex.org/W2250539671","https://openalex.org/W2253429366","https://openalex.org/W2338318698","https://openalex.org/W2404281525","https://openalex.org/W2470673105","https://openalex.org/W2587528408","https://openalex.org/W2788667846","https://openalex.org/W2896457183","https://openalex.org/W2951359136","https://openalex.org/W2963026768","https://openalex.org/W2963341956","https://openalex.org/W2963918774","https://openalex.org/W2964121744","https://openalex.org/W2964308564","https://openalex.org/W2964352358","https://openalex.org/W4297734170"],"related_works":["https://openalex.org/W3176438653","https://openalex.org/W2510206144","https://openalex.org/W2981628807","https://openalex.org/W4379875147","https://openalex.org/W4376528628","https://openalex.org/W3012393889","https://openalex.org/W2735080633","https://openalex.org/W3189091156","https://openalex.org/W2739554176","https://openalex.org/W4205999209"],"abstract_inverted_index":{"Multi-Label":[0],"Hierarchical":[1],"Text":[2],"Classification":[3],"(MLHTC)":[4],"is":[5],"the":[6,54,61,67,110],"task":[7],"of":[8,60,101],"categorizing":[9],"documents":[10],"into":[11],"one":[12],"or":[13],"more":[14],"topics":[15],"organized":[16],"in":[17,53,98],"an":[18,32],"hierarchical":[19],"taxonomy.":[20],"MLHTC":[21],"can":[22],"be":[23],"formulated":[24],"by":[25],"combining":[26],"multiple":[27],"binary":[28,48,89,118],"classification":[29,70],"problems":[30],"with":[31,85],"independent":[33],"classifier":[34,63],"for":[35],"each":[36],"category.":[37],"We":[38],"propose":[39],"a":[40,76],"novel":[41],"transfer":[42],"learning":[43,82],"based":[44],"strategy,":[45],"HTrans,":[46,73],"where":[47],"classifiers":[49,90,119],"at":[50],"lower":[51],"levels":[52],"hierarchy":[55],"are":[56,123],"initialized":[57],"using":[58],"parameters":[59],"parent":[62],"and":[64,105],"fine-tuned":[65],"on":[66,103,107,109],"child":[68],"category":[69],"task.":[71],"In":[72],"we":[74],"use":[75],"Gated":[77],"Recurrent":[78],"Unit":[79],"(GRU)-based":[80],"deep":[81],"architecture":[83],"coupled":[84],"attention.":[86],"Compared":[87],"to":[88],"trained":[91,120],"from":[92,121],"scratch,":[93],"our":[94],"HTrans":[95],"approach":[96],"results":[97],"significant":[99],"improvements":[100],"1%":[102],"micro-F1":[104],"3%":[106],"macro-F1":[108],"RCV1":[111],"dataset.":[112],"Our":[113],"experiments":[114],"also":[115],"show":[116],"that":[117],"scratch":[122],"significantly":[124],"better":[125],"than":[126],"single":[127],"multi-label":[128],"models.":[129]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":15},{"year":2024,"cited_by_count":21},{"year":2023,"cited_by_count":22},{"year":2022,"cited_by_count":14},{"year":2021,"cited_by_count":20},{"year":2020,"cited_by_count":12}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}