{"id":"https://openalex.org/W4285263440","doi":"https://doi.org/10.18653/v1/2022.acl-long.129","title":"Probing as Quantifying Inductive Bias","display_name":"Probing as Quantifying Inductive Bias","publication_year":2022,"publication_date":"2022-01-01","ids":{"openalex":"https://openalex.org/W4285263440","doi":"https://doi.org/10.18653/v1/2022.acl-long.129","mag":"3207167006"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2022.acl-long.129","doi":"https://doi.org/10.18653/v1/2022.acl-long.129","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2022.acl-long.129","pdf_url":"https://aclanthology.org/2022.acl-long.129.pdf","source":{"id":"https://openalex.org/S4393915740","display_name":"Proceedings of the conference - Association for Computational Linguistics. Meeting","issn_l":"0736-587X","issn":["0736-587X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"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 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":["crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://aclanthology.org/2022.acl-long.129.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5066728592","display_name":"Alexander Immer","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]},{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["CH","US"],"is_corresponding":false,"raw_author_name":"Alexander Immer","raw_affiliation_strings":["ETH Z\u00fcrich MIT"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ETH Z\u00fcrich MIT","institution_ids":["https://openalex.org/I35440088","https://openalex.org/I63966007"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087863947","display_name":"Lucas Torroba Hennigen","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]},{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["CH","US"],"is_corresponding":false,"raw_author_name":"Lucas Torroba Hennigen","raw_affiliation_strings":["ETH Z\u00fcrich MIT"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ETH Z\u00fcrich MIT","institution_ids":["https://openalex.org/I35440088","https://openalex.org/I63966007"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010706885","display_name":"Vincent Fortuin","orcid":"https://orcid.org/0000-0002-0640-2671","observed_orcids":["https://orcid.org/0000-0002-0640-2671"]},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]},{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["CH","US"],"is_corresponding":false,"raw_author_name":"Vincent Fortuin","raw_affiliation_strings":["ETH Z\u00fcrich MIT"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ETH Z\u00fcrich MIT","institution_ids":["https://openalex.org/I35440088","https://openalex.org/I63966007"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5061951606","display_name":"Ryan Cotterell","orcid":"https://orcid.org/0000-0003-4080-1833","observed_orcids":["https://orcid.org/0000-0003-4080-1833"]},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]},{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["CH","US"],"is_corresponding":false,"raw_author_name":"Ryan Cotterell","raw_affiliation_strings":["ETH Z\u00fcrich MIT"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ETH Z\u00fcrich MIT","institution_ids":["https://openalex.org/I35440088","https://openalex.org/I63966007"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.5715,"has_fulltext":true,"cited_by_count":19,"citation_normalized_percentile":{"value":0.86334454,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1839","last_page":"1851"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9502000212669373,"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":0.9502000212669373,"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":0.017400000244379044,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.010099999606609344,"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/probing","display_name":"probing","score":0.9300000071525574},{"id":"https://openalex.org/keywords/inductive-bias","display_name":"inductive bias","score":0.9769999980926514},{"id":"https://openalex.org/keywords/bayesian-framework","display_name":"Bayesian framework","score":0.8259999752044678},{"id":"https://openalex.org/keywords/fasttext","display_name":"FastText","score":0.6819999814033508},{"id":"https://openalex.org/keywords/bert","display_name":"BERT","score":0.996999979019165},{"id":"https://openalex.org/keywords/representation-learning","display_name":"representation learning","score":0.3449999988079071}],"concepts":[{"id":"https://openalex.org/C197352929","wikidata":"https://www.wikidata.org/wiki/Q1074074","display_name":"Inductive bias","level":4,"score":0.7951797842979431},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7143636345863342},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.6269250512123108},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.6116078495979309},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6043149828910828},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.5639134645462036},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5277947783470154},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.47954341769218445},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.43937593698501587},{"id":"https://openalex.org/C78780964","wikidata":"https://www.wikidata.org/wiki/Q7233193","display_name":"Position paper","level":2,"score":0.4114611744880676},{"id":"https://openalex.org/C28006648","wikidata":"https://www.wikidata.org/wiki/Q6934509","display_name":"Multi-task learning","level":3,"score":0.3735077977180481},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3399326801300049},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.0},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","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},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.18653/v1/2022.acl-long.129","doi":"https://doi.org/10.18653/v1/2022.acl-long.129","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2022.acl-long.129","pdf_url":"https://aclanthology.org/2022.acl-long.129.pdf","source":{"id":"https://openalex.org/S4393915740","display_name":"Proceedings of the conference - Association for Computational Linguistics. Meeting","issn_l":"0736-587X","issn":["0736-587X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"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 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},{"id":"mag:3207167006","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/pdf/2110.08388.pdf","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,"listed_in":[],"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":"pmh:oai:www.research-collection.ethz.ch:20.500.11850/570881","doi":null,"is_oa":true,"landing_page_url":"http://hdl.handle.net/20.500.11850/570881","pdf_url":null,"source":{"id":"https://openalex.org/S4306402302","display_name":"Repository for Publications and Research Data (ETH Zurich)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I35440088","host_organization_name":"ETH Zurich","host_organization_lineage":["https://openalex.org/I35440088"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics","raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"doi:10.3929/ethz-b-000570881","doi":"https://doi.org/10.3929/ethz-b-000570881","is_oa":true,"landing_page_url":"https://doi.org/10.3929/ethz-b-000570881","pdf_url":null,"source":{"id":"https://openalex.org/S7407051236","display_name":"ETH Z\u00fcrich Research Collection","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article-journal"}],"best_oa_location":{"id":"doi:10.18653/v1/2022.acl-long.129","doi":"https://doi.org/10.18653/v1/2022.acl-long.129","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2022.acl-long.129","pdf_url":"https://aclanthology.org/2022.acl-long.129.pdf","source":{"id":"https://openalex.org/S4393915740","display_name":"Proceedings of the conference - Association for Computational Linguistics. Meeting","issn_l":"0736-587X","issn":["0736-587X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"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 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320310638","display_name":"McGill University","ror":"https://ror.org/01pxwe438"},{"id":"https://openalex.org/F4320320924","display_name":"Schweizerischer Nationalfonds zur F\u00f6rderung der Wissenschaftlichen Forschung","ror":"https://ror.org/00yjd3n13"},{"id":"https://openalex.org/F4320331705","display_name":"Max Planck ETH Center for Learning Systems","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4285263440.pdf","grobid_xml":"https://content.openalex.org/works/W4285263440.grobid-xml"},"referenced_works_count":63,"referenced_works":["https://openalex.org/W806995027","https://openalex.org/W1493372406","https://openalex.org/W1503398984","https://openalex.org/W1522301498","https://openalex.org/W1601795611","https://openalex.org/W1663973292","https://openalex.org/W2070902649","https://openalex.org/W2127265454","https://openalex.org/W2130158090","https://openalex.org/W2139701068","https://openalex.org/W2140251433","https://openalex.org/W2166843037","https://openalex.org/W2309627465","https://openalex.org/W2396767181","https://openalex.org/W2493916176","https://openalex.org/W2515741950","https://openalex.org/W2525127255","https://openalex.org/W2529194139","https://openalex.org/W2605717780","https://openalex.org/W2607892599","https://openalex.org/W2787560479","https://openalex.org/W2788784374","https://openalex.org/W2895891096","https://openalex.org/W2906152891","https://openalex.org/W2914924671","https://openalex.org/W2922565841","https://openalex.org/W2946570717","https://openalex.org/W2946659172","https://openalex.org/W2950813464","https://openalex.org/W2962776659","https://openalex.org/W2963341956","https://openalex.org/W2963400886","https://openalex.org/W2963667932","https://openalex.org/W2964065120","https://openalex.org/W2964106018","https://openalex.org/W2964121744","https://openalex.org/W2964204621","https://openalex.org/W2965373594","https://openalex.org/W2970862333","https://openalex.org/W2975059944","https://openalex.org/W2979826702","https://openalex.org/W2981852735","https://openalex.org/W2990704537","https://openalex.org/W2993330478","https://openalex.org/W3013891696","https://openalex.org/W3015449890","https://openalex.org/W3026404337","https://openalex.org/W3071011332","https://openalex.org/W3082274269","https://openalex.org/W3090805418","https://openalex.org/W3091782154","https://openalex.org/W3092154909","https://openalex.org/W3124034626","https://openalex.org/W3140968660","https://openalex.org/W3155161741","https://openalex.org/W3162587184","https://openalex.org/W3175206595","https://openalex.org/W3175351491","https://openalex.org/W3196649867","https://openalex.org/W3206180216","https://openalex.org/W4253067820","https://openalex.org/W6631349028","https://openalex.org/W6893675597"],"related_works":["https://openalex.org/W3207167006","https://openalex.org/W3022518881","https://openalex.org/W3116152597","https://openalex.org/W4382202746","https://openalex.org/W3102812725","https://openalex.org/W3098300729","https://openalex.org/W3090805418","https://openalex.org/W3169436637","https://openalex.org/W4389520189","https://openalex.org/W3023780163"],"abstract_inverted_index":{"Pre-trained":[0],"contextual":[1,58],"representations":[2,110],"have":[3,17],"led":[4],"to":[5,20,50,67,77,79,100,128,144,166],"dramatic":[6],"performance":[7,15],"improvements":[8,16],"on":[9,112],"a":[10,47,52,113,118,145,175],"range":[11],"of":[12,36,45,62,87,97,105,137,147],"downstream":[13],"tasks.Such":[14],"motivated":[18],"researchers":[19,32],"quantify":[21,33,129],"and":[22,73,81,125],"understand":[23],"the":[24,34,57,71,84,92,95,103,109,130,134,138],"linguistic":[25,37,53],"information":[26,38],"encoded":[27],"in":[28,70,161],"these":[29],"representations.In":[30],"general,":[31],"amount":[35,104],"through":[39],"probing,":[40],"an":[41],"endeavor":[42],"which":[43],"consists":[44],"training":[46],"supervised":[48],"model":[49],"predict":[51],"property":[54],"directly":[55],"from":[56],"representations.Unfortunately,":[59],"this":[60,88,123],"definition":[61],"probing":[63,98],"has":[64,74],"been":[65,75],"subject":[66],"extensive":[68],"criticism":[69],"literature,":[72],"observed":[76],"lead":[78],"paradoxical":[80],"counterintuitive":[82],"results.In":[83],"theoretical":[85],"portion":[86,136],"paper,":[89,139],"we":[90,140,163],"take":[91],"position":[93],"that":[94,108,121,152],"goal":[96,124],"ought":[99],"be":[101],"measuring":[102],"inductive":[106,132,177],"bias":[107,178],"encode":[111],"specific":[114],"task.We":[115],"further":[116],"describe":[117],"Bayesian":[119],"framework":[120,143,155],"operationalizes":[122],"allows":[126],"us":[127],"representations'":[131],"bias.In":[133],"empirical":[135],"apply":[141],"our":[142,153],"variety":[146],"NLP":[148],"tasks.Our":[149],"results":[150],"suggest":[151],"proposed":[154],"alleviates":[156],"many":[157],"previous":[158],"problems":[159],"found":[160],"probing.Moreover,":[162],"are":[164],"able":[165],"offer":[167,174],"concrete":[168],"evidence":[169],"that-for":[170],"some":[171],"tasks-fastText":[172],"can":[173],"better":[176],"than":[179],"BERT.":[180],"1":[181,185],"*":[182],"Equal":[183],"contribution.":[184],"Our":[186],"code":[187],"is":[188],"available":[189],"at":[190],"https://github.com/":[191],"rycolab/evidence-probing.":[192]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":9},{"year":2022,"cited_by_count":2}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2022-07-14T00:00:00"}