{"id":"https://openalex.org/W2977420403","doi":"https://doi.org/10.1109/ijcnn.2019.8852398","title":"Improving Universal Language Model Fine-Tuning using Attention Mechanism","display_name":"Improving Universal Language Model Fine-Tuning using Attention Mechanism","publication_year":2019,"publication_date":"2019-07-01","ids":{"openalex":"https://openalex.org/W2977420403","doi":"https://doi.org/10.1109/ijcnn.2019.8852398","mag":"2977420403"},"language":"en","primary_location":{"is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn.2019.8852398","pdf_url":null,"source":{"id":"https://openalex.org/S4363607707","display_name":"2022 International Joint Conference on Neural Networks (IJCNN)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_indexed_in_scopus":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":null,"is_accepted":false,"is_published":false},"type":"article","type_crossref":"proceedings-article","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/A5062021162","display_name":"Fl\u00e1vio Santos","orcid":"https://orcid.org/0000-0003-2378-5376"},"institutions":[{"id":"https://openalex.org/I25112270","display_name":"Universidade Federal de Pernambuco","ror":"https://ror.org/047908t24","country_code":"BR","type":"education","lineage":["https://openalex.org/I25112270"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Flavio A. O. Santos","raw_affiliation_strings":["Centro de Inform\u00e1tica, Universidade Federal de Pernambuco, Recife, PE, Brazil"],"affiliations":[{"raw_affiliation_string":"Centro de Inform\u00e1tica, Universidade Federal de Pernambuco, Recife, PE, Brazil","institution_ids":["https://openalex.org/I25112270"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077672144","display_name":"K. L. Ponce-Guevara","orcid":"https://orcid.org/0000-0003-3112-739X"},"institutions":[{"id":"https://openalex.org/I25112270","display_name":"Universidade Federal de Pernambuco","ror":"https://ror.org/047908t24","country_code":"BR","type":"education","lineage":["https://openalex.org/I25112270"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"K.L. Ponce-Guevara","raw_affiliation_strings":["Centro de Inform\u00e1tica, Universidade Federal de Pernambuco, Recife, PE, Brazil"],"affiliations":[{"raw_affiliation_string":"Centro de Inform\u00e1tica, Universidade Federal de Pernambuco, Recife, PE, Brazil","institution_ids":["https://openalex.org/I25112270"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021701067","display_name":"David Mac\u00eado","orcid":"https://orcid.org/0000-0002-2527-4548"},"institutions":[{"id":"https://openalex.org/I25112270","display_name":"Universidade Federal de Pernambuco","ror":"https://ror.org/047908t24","country_code":"BR","type":"education","lineage":["https://openalex.org/I25112270"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"David Macedo","raw_affiliation_strings":["Centro de Inform\u00e1tica, Universidade Federal de Pernambuco, Recife, PE, Brazil"],"affiliations":[{"raw_affiliation_string":"Centro de Inform\u00e1tica, Universidade Federal de Pernambuco, Recife, PE, Brazil","institution_ids":["https://openalex.org/I25112270"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5086345001","display_name":"Cleber Zanchettin","orcid":"https://orcid.org/0000-0001-6421-9747"},"institutions":[{"id":"https://openalex.org/I25112270","display_name":"Universidade Federal de Pernambuco","ror":"https://ror.org/047908t24","country_code":"BR","type":"education","lineage":["https://openalex.org/I25112270"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Cleber Zanchettin","raw_affiliation_strings":["Centro de Inform\u00e1tica, Universidade Federal de Pernambuco, Recife, PE, Brazil"],"affiliations":[{"raw_affiliation_string":"Centro de Inform\u00e1tica, Universidade Federal de Pernambuco, Recife, PE, Brazil","institution_ids":["https://openalex.org/I25112270"]}]}],"institution_assertions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.214866,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":61,"max":69},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"7"},"is_retracted":false,"is_paratext":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9999,"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":0.9999,"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":0.9999,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9991,"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":[],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7257073},{"id":"https://openalex.org/C89611455","wikidata":"https://www.wikidata.org/wiki/Q6804646","display_name":"Mechanism (biology)","level":2,"score":0.68539304},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.42882428},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.29495615},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.08004546},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn.2019.8852398","pdf_url":null,"source":{"id":"https://openalex.org/S4363607707","display_name":"2022 International Joint Conference on Neural Networks (IJCNN)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_indexed_in_scopus":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":null,"is_accepted":false,"is_published":false}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.86,"id":"https://metadata.un.org/sdg/4","display_name":"Quality education"}],"grants":[],"datasets":[],"versions":[],"referenced_works_count":45,"referenced_works":["https://openalex.org/W1514535095","https://openalex.org/W1832693441","https://openalex.org/W1903029394","https://openalex.org/W1967981232","https://openalex.org/W1972085588","https://openalex.org/W2012422639","https://openalex.org/W2064675550","https://openalex.org/W2108598243","https://openalex.org/W2113459411","https://openalex.org/W2117130368","https://openalex.org/W2153579005","https://openalex.org/W2155541015","https://openalex.org/W2158339117","https://openalex.org/W2165698076","https://openalex.org/W2168681026","https://openalex.org/W2170240176","https://openalex.org/W2250539671","https://openalex.org/W2254361154","https://openalex.org/W2493916176","https://openalex.org/W2525332836","https://openalex.org/W2556468274","https://openalex.org/W2556888587","https://openalex.org/W2578711421","https://openalex.org/W2587528408","https://openalex.org/W2740721704","https://openalex.org/W2756381707","https://openalex.org/W2765178087","https://openalex.org/W2767434619","https://openalex.org/W2919115771","https://openalex.org/W2950141408","https://openalex.org/W2962676330","https://openalex.org/W2962743139","https://openalex.org/W2963012544","https://openalex.org/W2963026768","https://openalex.org/W2963563735","https://openalex.org/W2963706742","https://openalex.org/W2963756346","https://openalex.org/W2963908579","https://openalex.org/W3093419064","https://openalex.org/W4294170691","https://openalex.org/W4294375521","https://openalex.org/W4298422451","https://openalex.org/W4300996741","https://openalex.org/W4302343710","https://openalex.org/W854541894"],"related_works":["https://openalex.org/W4391913857","https://openalex.org/W2748952813","https://openalex.org/W2478288626","https://openalex.org/W2390279801","https://openalex.org/W2382997850","https://openalex.org/W2382290278","https://openalex.org/W2376932109","https://openalex.org/W2358668433","https://openalex.org/W2350741829","https://openalex.org/W2001405890"],"abstract_inverted_index":{"Inductive":[0],"transfer":[1,24,54],"learning":[2,25],"is":[3,16,29,42,98],"widespread":[4],"in":[5,10,27,124,132],"computer":[6],"vision":[7],"applications.":[8],"However,":[9],"natural":[11],"language":[12,51],"processing":[13],"(NLP)":[14],"applications":[15],"still":[17],"an":[18,79],"under-explored":[19],"area.":[20],"The":[21,36,96],"most":[22,102],"common":[23],"method":[26],"NLP":[28],"the":[30,62,75,101,106,121,129],"use":[31],"of":[32,78,105,134],"pre-trained":[33],"word":[34],"embeddings.":[35],"Universal":[37],"Language":[38],"Model":[39],"Fine-Tuning":[40],"(ULMFiT)":[41],"a":[43,50,58,67,92],"recent":[44],"approach":[45,123],"which":[46],"proposes":[47],"to":[48,57,73,84,99],"train":[49],"model":[52],"and":[53,69,87,116,127],"its":[55],"knowledge":[56],"final":[59],"classifier.":[60],"During":[61],"classification":[63],"step,":[64],"ULMFiT":[65],"uses":[66],"max":[68,86,115],"average":[70,88,117],"pooling":[71,89],"layer":[72],"select":[74],"useful":[76],"information":[77,104],"embedding":[80,107],"sequence.":[81],"We":[82,119],"propose":[83],"replace":[85],"layers":[90],"with":[91],"soft":[93],"attention":[94],"mechanism.":[95],"goal":[97],"learn":[100],"important":[103],"sequence":[108],"rather":[109],"than":[110],"assuming":[111],"that":[112],"they":[113],"are":[114],"values.":[118],"evaluate":[120],"proposed":[122],"six":[125],"datasets":[126],"achieve":[128],"best":[130],"performance":[131],"all":[133],"them":[135],"against":[136],"literature":[137],"approaches.":[138]},"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W2977420403","counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2025-01-18T00:02:17.779100","created_date":"2019-10-10"}