{"id":"https://openalex.org/W2921848006","doi":"https://doi.org/10.18653/v1/w19-4302","title":"To Tune or Not to Tune? Adapting Pretrained Representations to Diverse Tasks","display_name":"To Tune or Not to Tune? Adapting Pretrained Representations to Diverse Tasks","publication_year":2019,"publication_date":"2019-01-01","ids":{"openalex":"https://openalex.org/W2921848006","doi":"https://doi.org/10.18653/v1/w19-4302","mag":"2921848006"},"language":"en","primary_location":{"id":"doi:10.18653/v1/w19-4302","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w19-4302","pdf_url":"https://www.aclweb.org/anthology/W19-4302.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 4th Workshop on Representation Learning for NLP (RepL4NLP-2019)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/W19-4302.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101509445","display_name":"Matthew E. Peters","orcid":"https://orcid.org/0000-0002-2105-2585"},"institutions":[{"id":"https://openalex.org/I4210156221","display_name":"Allen Institute for Artificial Intelligence","ror":"https://ror.org/05w520734","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4210156221"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Matthew E. Peters","raw_affiliation_strings":["Allen Institute for Artificial Intelligence, Seattle, USA","ALLEN INSTITUTE FOR ARTIFICIAL INTELLIGENCE"],"affiliations":[{"raw_affiliation_string":"Allen Institute for Artificial Intelligence, Seattle, USA","institution_ids":["https://openalex.org/I4210156221"]},{"raw_affiliation_string":"ALLEN INSTITUTE FOR ARTIFICIAL INTELLIGENCE","institution_ids":["https://openalex.org/I4210156221"]}]},{"author_position":"middle","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"]},{"id":"https://openalex.org/I4210156221","display_name":"Allen Institute for Artificial Intelligence","ror":"https://ror.org/05w520734","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4210156221"]}],"countries":["IE","US"],"is_corresponding":false,"raw_author_name":"Sebastian Ruder","raw_affiliation_strings":["Aylien Ltd., Dublin, Ireland","Insight Research Centre, National University of Ireland, Galway, Ireland","ALLEN INSTITUTE FOR ARTIFICIAL INTELLIGENCE"],"affiliations":[{"raw_affiliation_string":"Aylien Ltd., Dublin, Ireland","institution_ids":[]},{"raw_affiliation_string":"Insight Research Centre, National University of Ireland, Galway, Ireland","institution_ids":["https://openalex.org/I188760350"]},{"raw_affiliation_string":"ALLEN INSTITUTE FOR ARTIFICIAL INTELLIGENCE","institution_ids":["https://openalex.org/I4210156221"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5088517824","display_name":"Noah A. Smith","orcid":"https://orcid.org/0000-0002-2310-6380"},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]},{"id":"https://openalex.org/I2801851002","display_name":"Harvard University Press","ror":"https://ror.org/006v7bf86","country_code":"US","type":"other","lineage":["https://openalex.org/I136199984","https://openalex.org/I2801851002"]},{"id":"https://openalex.org/I4210156221","display_name":"Allen Institute for Artificial Intelligence","ror":"https://ror.org/05w520734","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4210156221"]},{"id":"https://openalex.org/I58610484","display_name":"Seattle University","ror":"https://ror.org/02jqc0m91","country_code":"US","type":"education","lineage":["https://openalex.org/I58610484"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Noah A. Smith","raw_affiliation_strings":["Allen Institute for Artificial Intelligence, Seattle, USA","Paul G. Allen School of CSE, University of Washington, Seattle, USA","Harvard University, Cambridge, United States"],"affiliations":[{"raw_affiliation_string":"Allen Institute for Artificial Intelligence, Seattle, USA","institution_ids":["https://openalex.org/I4210156221"]},{"raw_affiliation_string":"Paul G. Allen School of CSE, University of Washington, Seattle, USA","institution_ids":["https://openalex.org/I201448701","https://openalex.org/I58610484"]},{"raw_affiliation_string":"Harvard University, Cambridge, United States","institution_ids":["https://openalex.org/I2801851002"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5101509445"],"corresponding_institution_ids":["https://openalex.org/I4210156221"],"apc_list":null,"apc_paid":null,"fwci":7.3598,"has_fulltext":true,"cited_by_count":58,"citation_normalized_percentile":{"value":0.97642659,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"7","last_page":"14"},"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9998000264167786,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9993000030517578,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.7521700859069824},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.6611998677253723},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6603761911392212},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.6099975109100342},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5977163314819336},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5873799324035645},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.5639001131057739},{"id":"https://openalex.org/keywords/ask-price","display_name":"Ask price","score":0.5438331961631775},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5404502153396606},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.5352944135665894},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.5075863599777222},{"id":"https://openalex.org/keywords/fine-tuning","display_name":"Fine-tuning","score":0.4269862473011017},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.40633782744407654},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.13153481483459473},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.11643171310424805},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.06536868214607239}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7521700859069824},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.6611998677253723},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6603761911392212},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.6099975109100342},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5977163314819336},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5873799324035645},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5639001131057739},{"id":"https://openalex.org/C90329073","wikidata":"https://www.wikidata.org/wiki/Q914232","display_name":"Ask price","level":2,"score":0.5438331961631775},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5404502153396606},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5352944135665894},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.5075863599777222},{"id":"https://openalex.org/C157524613","wikidata":"https://www.wikidata.org/wiki/Q2828883","display_name":"Fine-tuning","level":2,"score":0.4269862473011017},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.40633782744407654},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.13153481483459473},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.11643171310424805},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.06536868214607239},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C136264566","wikidata":"https://www.wikidata.org/wiki/Q159810","display_name":"Economy","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},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.18653/v1/w19-4302","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w19-4302","pdf_url":"https://www.aclweb.org/anthology/W19-4302.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 4th Workshop on Representation Learning for NLP (RepL4NLP-2019)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1903.05987","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1903.05987","pdf_url":"https://arxiv.org/pdf/1903.05987","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":null,"raw_type":"text"},{"id":"mag:2921848006","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1903.05987.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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.1903.05987","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1903.05987","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":"article"}],"best_oa_location":{"id":"doi:10.18653/v1/w19-4302","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w19-4302","pdf_url":"https://www.aclweb.org/anthology/W19-4302.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 4th Workshop on Representation Learning for NLP (RepL4NLP-2019)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2921848006.pdf","grobid_xml":"https://content.openalex.org/works/W2921848006.grobid-xml"},"referenced_works_count":37,"referenced_works":["https://openalex.org/W131533222","https://openalex.org/W1486649854","https://openalex.org/W1832693441","https://openalex.org/W2109553965","https://openalex.org/W2144578941","https://openalex.org/W2147880316","https://openalex.org/W2153579005","https://openalex.org/W2153653739","https://openalex.org/W2158139315","https://openalex.org/W2165698076","https://openalex.org/W2250539671","https://openalex.org/W2250790822","https://openalex.org/W2251939518","https://openalex.org/W2296283641","https://openalex.org/W2608787653","https://openalex.org/W2768282280","https://openalex.org/W2785885194","https://openalex.org/W2786858562","https://openalex.org/W2793978524","https://openalex.org/W2799054028","https://openalex.org/W2896457183","https://openalex.org/W2901394229","https://openalex.org/W2949667497","https://openalex.org/W2962739339","https://openalex.org/W2962776659","https://openalex.org/W2963026768","https://openalex.org/W2963090765","https://openalex.org/W2963403868","https://openalex.org/W2963644595","https://openalex.org/W2963756346","https://openalex.org/W2963846996","https://openalex.org/W2963918774","https://openalex.org/W2964121744","https://openalex.org/W2964125718","https://openalex.org/W2964352358","https://openalex.org/W3104033643","https://openalex.org/W3106003309"],"related_works":["https://openalex.org/W2963341956","https://openalex.org/W2965373594","https://openalex.org/W2970352191","https://openalex.org/W2963403868","https://openalex.org/W2962739339","https://openalex.org/W2250539671","https://openalex.org/W2963026768","https://openalex.org/W2963310665","https://openalex.org/W2064675550","https://openalex.org/W2251939518","https://openalex.org/W2963846996","https://openalex.org/W1522301498","https://openalex.org/W2978017171","https://openalex.org/W2970597249","https://openalex.org/W2964303116","https://openalex.org/W2888329843","https://openalex.org/W3175557894","https://openalex.org/W2978670439","https://openalex.org/W2898700502","https://openalex.org/W131533222"],"abstract_inverted_index":{"While":[0],"most":[1,34],"previous":[2],"work":[3],"has":[4],"focused":[5],"on":[6,31,75],"different":[7],"pretraining":[8,80],"objectives":[9],"and":[10,47,81,91],"architectures":[11],"for":[12,88,98],"transfer":[13],"learning,":[14],"we":[15],"ask":[16],"how":[17],"to":[18,24],"best":[19],"adapt":[20],"the":[21,32,42,50,66,76,79,99],"pretrained":[22,43,51],"model":[23],"a":[25,93],"given":[26],"target":[27,82],"task.":[28],"We":[29,84],"focus":[30],"two":[33,61],"common":[35],"forms":[36],"of":[37,69,78,95],"adaptation,":[38],"feature":[39,72],"extraction":[40,73],"(where":[41],"weights":[44],"are":[45],"frozen),":[46],"directly":[48],"finetuning":[49],"model.":[52],"Our":[53],"empirical":[54],"results":[55],"across":[56],"diverse":[57],"NLP":[58,100],"tasks":[59],"with":[60],"stateof-the-art":[62],"models":[63],"show":[64],"that":[65],"relative":[67],"performance":[68],"fine-tuning":[70],"vs.":[71],"depends":[74],"similarity":[77],"tasks.":[83],"explore":[85],"possible":[86],"explanations":[87],"this":[89],"finding":[90],"provide":[92],"set":[94],"adaptation":[96],"guidelines":[97],"practitioner.":[101]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":12},{"year":2020,"cited_by_count":26},{"year":2019,"cited_by_count":11}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}