{"id":"https://openalex.org/W2798812533","doi":"https://doi.org/10.18653/v1/p18-1031","title":"Universal Language Model Fine-tuning for Text Classification","display_name":"Universal Language Model Fine-tuning for Text Classification","publication_year":2018,"publication_date":"2018-01-01","ids":{"openalex":"https://openalex.org/W2798812533","doi":"https://doi.org/10.18653/v1/p18-1031","mag":"2798812533"},"language":"en","primary_location":{"id":"doi:10.18653/v1/p18-1031","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p18-1031","pdf_url":"https://www.aclweb.org/anthology/P18-1031.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 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/P18-1031.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102749721","display_name":"Jeremy Howard","orcid":"https://orcid.org/0000-0001-6216-3540"},"institutions":[{"id":"https://openalex.org/I137902535","display_name":"North Carolina State University","ror":"https://ror.org/04tj63d06","country_code":"US","type":"education","lineage":["https://openalex.org/I137902535"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jeremy Howard","raw_affiliation_strings":["North Carolina State University, Raleigh, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"North Carolina State University, Raleigh, United States","institution_ids":["https://openalex.org/I137902535"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5037310413","display_name":"Sebastian Ruder","orcid":null},"institutions":[{"id":"https://openalex.org/I188760350","display_name":"Ollscoil na Gaillimhe \u2013 University of Galway","ror":"https://ror.org/03bea9k73","country_code":"IE","type":"education","lineage":["https://openalex.org/I188760350"]}],"countries":["IE"],"is_corresponding":false,"raw_author_name":"Sebastian Ruder","raw_affiliation_strings":["Ollscoil na Gaillimhe \u2013 University of Galway, Galway, Ireland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ollscoil na Gaillimhe \u2013 University of Galway, Galway, Ireland","institution_ids":["https://openalex.org/I188760350"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":341,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"328","last_page":"339"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9868999719619751,"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":0.9868999719619751,"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":0.9634000062942505,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9510999917984009,"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/scratch","display_name":"Scratch","score":0.9122046232223511},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8367975950241089},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.7414246797561646},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6506626009941101},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.6322728395462036},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.6046342253684998},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.59498131275177},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5684478878974915},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.5223656296730042},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.41563642024993896},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3773486316204071},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.1360759437084198}],"concepts":[{"id":"https://openalex.org/C2781235140","wikidata":"https://www.wikidata.org/wiki/Q275131","display_name":"Scratch","level":2,"score":0.9122046232223511},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8367975950241089},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.7414246797561646},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6506626009941101},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.6322728395462036},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.6046342253684998},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.59498131275177},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5684478878974915},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5223656296730042},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.41563642024993896},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3773486316204071},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.1360759437084198},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.18653/v1/p18-1031","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p18-1031","pdf_url":"https://www.aclweb.org/anthology/P18-1031.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 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1801.06146","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1801.06146","pdf_url":"https://arxiv.org/pdf/1801.06146","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"mag:2798812533","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1801.06146v5","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.1801.06146","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1801.06146","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.18653/v1/p18-1031","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p18-1031","pdf_url":"https://www.aclweb.org/anthology/P18-1031.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 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.8299999833106995}],"awards":[{"id":"https://openalex.org/G1383882326","display_name":null,"funder_award_id":"SFI/12/RC/","funder_id":"https://openalex.org/F4320320847","funder_display_name":"Science Foundation Ireland"},{"id":"https://openalex.org/G2881606312","display_name":null,"funder_award_id":"SFI/12/RC/2289","funder_id":"https://openalex.org/F4320320847","funder_display_name":"Science Foundation Ireland"},{"id":"https://openalex.org/G5098725405","display_name":null,"funder_award_id":"12/RC/","funder_id":"https://openalex.org/F4320320847","funder_display_name":"Science Foundation Ireland"},{"id":"https://openalex.org/G6654329577","display_name":null,"funder_award_id":"Grant Number SFI/12/RC/2289","funder_id":"https://openalex.org/F4320320847","funder_display_name":"Science Foundation Ireland"},{"id":"https://openalex.org/G7362007176","display_name":"INSIGHT - Irelands Big Data and Analytics Research Centre","funder_award_id":"12/RC/2289","funder_id":"https://openalex.org/F4320320847","funder_display_name":"Science Foundation Ireland"}],"funders":[{"id":"https://openalex.org/F4320320847","display_name":"Science Foundation Ireland","ror":"https://ror.org/0271asj38"},{"id":"https://openalex.org/F4320321056","display_name":"Irish Research Council","ror":"https://ror.org/051xex213"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2798812533.pdf","grobid_xml":"https://content.openalex.org/works/W2798812533.grobid-xml"},"referenced_works_count":1,"referenced_works":["https://openalex.org/W4234915122"],"related_works":["https://openalex.org/W2250539671","https://openalex.org/W2896457183","https://openalex.org/W2965373594","https://openalex.org/W2787560479","https://openalex.org/W2626778328","https://openalex.org/W2950133940","https://openalex.org/W2064675550","https://openalex.org/W2950577311","https://openalex.org/W2493916176","https://openalex.org/W2194775991","https://openalex.org/W2963026768","https://openalex.org/W2964121744","https://openalex.org/W2743945814","https://openalex.org/W2132339004","https://openalex.org/W2950813464","https://openalex.org/W2163605009","https://openalex.org/W2964308564","https://openalex.org/W2557283755","https://openalex.org/W2165698076","https://openalex.org/W2996428491"],"abstract_inverted_index":{"Inductive":[0],"transfer":[1,30],"learning":[2,31],"has":[3],"greatly":[4],"impacted":[5],"computer":[6],"vision,":[7],"but":[8],"existing":[9],"approaches":[10],"in":[11,40],"NLP":[12],"still":[13],"require":[14],"task-specific":[15],"modifications":[16],"and":[17,42,97],"training":[18,85],"from":[19,86],"scratch.":[20],"We":[21,92],"propose":[22],"Universal":[23],"Language":[24],"Model":[25],"Fine-tuning":[26],"(ULMFiT),":[27],"an":[28],"effective":[29],"method":[32,54],"that":[33,45],"can":[34],"be":[35],"applied":[36],"to":[37],"any":[38],"task":[39],"NLP,":[41],"introduce":[43],"techniques":[44],"are":[46],"key":[47],"for":[48],"fine-tuning":[49],"a":[50],"language":[51],"model.":[52],"Our":[53],"significantly":[55],"outperforms":[56],"the":[57,65,70,82],"state-of-the-art":[58],"on":[59,69,88],"six":[60],"text":[61],"classification":[62],"tasks,":[63],"reducing":[64],"error":[66],"by":[67],"18-24%":[68],"majority":[71],"of":[72,84],"datasets.":[73],"Furthermore,":[74],"with":[75],"only":[76],"100":[77,89],"labeled":[78],"examples,":[79],"it":[80],"matches":[81],"performance":[83],"scratch":[87],"more":[90],"data.":[91],"opensource":[93],"our":[94],"pretrained":[95],"models":[96],"code":[98],"1":[99],".":[100]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":14},{"year":2024,"cited_by_count":35},{"year":2023,"cited_by_count":41},{"year":2022,"cited_by_count":42},{"year":2021,"cited_by_count":84},{"year":2020,"cited_by_count":77},{"year":2019,"cited_by_count":44},{"year":2018,"cited_by_count":3}],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2025-10-10T00:00:00"}