{"id":"https://openalex.org/W2973154008","doi":"https://doi.org/10.18653/v1/w19-4825","title":"Open Sesame: Getting inside BERT\u2019s Linguistic Knowledge","display_name":"Open Sesame: Getting inside BERT\u2019s Linguistic Knowledge","publication_year":2019,"publication_date":"2019-01-01","ids":{"openalex":"https://openalex.org/W2973154008","doi":"https://doi.org/10.18653/v1/w19-4825","mag":"2973154008"},"language":"en","primary_location":{"id":"doi:10.18653/v1/w19-4825","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w19-4825","pdf_url":"https://www.aclweb.org/anthology/W19-4825.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 2019 ACL Workshop BlackboxNLP: Analyzing and Interpreting Neural Networks for NLP","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/W19-4825.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5086311958","display_name":"Yongjie Lin","orcid":"https://orcid.org/0000-0001-6263-7187"},"institutions":[{"id":"https://openalex.org/I32971472","display_name":"Yale University","ror":"https://ror.org/03v76x132","country_code":"US","type":"education","lineage":["https://openalex.org/I32971472"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yongjie Lin","raw_affiliation_strings":["Department of Computer Science, Yale University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Yale University","institution_ids":["https://openalex.org/I32971472"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081057611","display_name":"Yi Chern Tan","orcid":null},"institutions":[{"id":"https://openalex.org/I32971472","display_name":"Yale University","ror":"https://ror.org/03v76x132","country_code":"US","type":"education","lineage":["https://openalex.org/I32971472"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yi Chern Tan","raw_affiliation_strings":["Department of Computer Science, Yale University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Yale University","institution_ids":["https://openalex.org/I32971472"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5071457812","display_name":"Robert Frank","orcid":"https://orcid.org/0000-0001-9253-1658"},"institutions":[{"id":"https://openalex.org/I32971472","display_name":"Yale University","ror":"https://ror.org/03v76x132","country_code":"US","type":"education","lineage":["https://openalex.org/I32971472"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Robert Frank","raw_affiliation_strings":["Department of Linguistics, Yale University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Linguistics, Yale University","institution_ids":["https://openalex.org/I32971472"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I32971472"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":245,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"241","last_page":"253"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10465","display_name":"Neurobiology of Language and Bilingualism","score":0.9994999766349792,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},"topics":[{"id":"https://openalex.org/T10465","display_name":"Neurobiology of Language and Bilingualism","score":0.9994999766349792,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9950000047683716,"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/T10034","display_name":"Syntax, Semantics, Linguistic Variation","score":0.9871000051498413,"subfield":{"id":"https://openalex.org/subfields/1203","display_name":"Language and Linguistics"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7722140550613403},{"id":"https://openalex.org/keywords/antecedent","display_name":"Antecedent (behavioral psychology)","score":0.696928083896637},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6123875379562378},{"id":"https://openalex.org/keywords/encode","display_name":"ENCODE","score":0.5630811452865601},{"id":"https://openalex.org/keywords/anaphora","display_name":"Anaphora (linguistics)","score":0.55454421043396},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5529239773750305},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5379316210746765},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.5002148151397705},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.4461438059806824},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.4449879825115204},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.4381260871887207},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.13819020986557007}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7722140550613403},{"id":"https://openalex.org/C2781256819","wikidata":"https://www.wikidata.org/wiki/Q16828835","display_name":"Antecedent (behavioral psychology)","level":2,"score":0.696928083896637},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6123875379562378},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.5630811452865601},{"id":"https://openalex.org/C2781449363","wikidata":"https://www.wikidata.org/wiki/Q156751","display_name":"Anaphora (linguistics)","level":3,"score":0.55454421043396},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5529239773750305},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5379316210746765},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.5002148151397705},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.4461438059806824},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.4449879825115204},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.4381260871887207},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.13819020986557007},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"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/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"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/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0},{"id":"https://openalex.org/C138268822","wikidata":"https://www.wikidata.org/wiki/Q1051925","display_name":"Resolution (logic)","level":2,"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/C138496976","wikidata":"https://www.wikidata.org/wiki/Q175002","display_name":"Developmental psychology","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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/w19-4825","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w19-4825","pdf_url":"https://www.aclweb.org/anthology/W19-4825.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 2019 ACL Workshop BlackboxNLP: Analyzing and Interpreting Neural Networks for NLP","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/w19-4825","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w19-4825","pdf_url":"https://www.aclweb.org/anthology/W19-4825.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 2019 ACL Workshop BlackboxNLP: Analyzing and Interpreting Neural Networks for NLP","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.7400000095367432,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2973154008.pdf","grobid_xml":"https://content.openalex.org/works/W2973154008.grobid-xml"},"referenced_works_count":38,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1951216520","https://openalex.org/W2008652694","https://openalex.org/W2055457833","https://openalex.org/W2133564696","https://openalex.org/W2135547275","https://openalex.org/W2153579005","https://openalex.org/W2167525509","https://openalex.org/W2250539671","https://openalex.org/W2320129592","https://openalex.org/W2549835527","https://openalex.org/W2742947407","https://openalex.org/W2788924045","https://openalex.org/W2792641098","https://openalex.org/W2799051177","https://openalex.org/W2886663262","https://openalex.org/W2888922637","https://openalex.org/W2896457183","https://openalex.org/W2910243263","https://openalex.org/W2922523190","https://openalex.org/W2924690340","https://openalex.org/W2934032625","https://openalex.org/W2946359678","https://openalex.org/W2952208026","https://openalex.org/W2962739339","https://openalex.org/W2963026768","https://openalex.org/W2963341956","https://openalex.org/W2963430224","https://openalex.org/W2963614302","https://openalex.org/W2963751529","https://openalex.org/W2964121744","https://openalex.org/W2964222268","https://openalex.org/W2964243640","https://openalex.org/W2964308564","https://openalex.org/W4253525579","https://openalex.org/W4288351520","https://openalex.org/W4288631803","https://openalex.org/W4294170691"],"related_works":["https://openalex.org/W3157556506","https://openalex.org/W2045494691","https://openalex.org/W2884082915","https://openalex.org/W2353619472","https://openalex.org/W2950376965","https://openalex.org/W2224947892","https://openalex.org/W2353968314","https://openalex.org/W1853461754","https://openalex.org/W2615457777","https://openalex.org/W3096231636"],"abstract_inverted_index":{"How":[0],"and":[1,75],"to":[2,31,41,105,132,137],"what":[3],"extent":[4],"does":[5],"BERT":[6,23,91],"encode":[7],"syntactically-sensitive":[8],"hierarchical":[9,125,138],"information":[10,94],"or":[11],"positionally-sensitive":[12],"linear":[13],"information?":[14],"Recent":[15],"work":[16],"has":[17],"shown":[18],"that":[19,28,90,115,140],"contextual":[20],"representations":[21,117],"like":[22],"perform":[24],"well":[25,98],"on":[26,57,99,109],"tasks":[27],"require":[29],"sensitivity":[30,136],"linguistic":[32],"structure.":[33],"We":[34,112],"present":[35],"here":[36],"two":[37],"studies":[38],"which":[39],"aim":[40],"provide":[42],"a":[43,79,106],"better":[44],"understanding":[45],"of":[46,49,54,60,72,82,124,146],"the":[47,58,67,134],"nature":[48],"BERT's":[50,70,116],"representations.":[51],"The":[52],"first":[53],"these":[55],"focuses":[56],"identification":[59],"structurally-defined":[61],"elements":[62],"using":[63],"diagnostic":[64],"classifiers,":[65],"while":[66],"second":[68],"explores":[69],"representation":[71],"subject-verb":[73],"agreement":[74],"anaphor-antecedent":[76],"dependencies":[77],"through":[78],"quantitative":[80],"assessment":[81],"self-attention":[83],"vectors.":[84],"In":[85],"both":[86],"cases,":[87],"we":[88],"find":[89],"encodes":[92],"positional":[93],"about":[95],"word":[96],"tokens":[97],"its":[100],"lower":[101],"layers,":[102],"but":[103],"switches":[104],"hierarchically-oriented":[107],"encoding":[108],"higher":[110],"layers.":[111],"conclude":[113],"then":[114],"do":[118,129],"indeed":[119],"model":[120],"linguistically":[121],"relevant":[122],"aspects":[123],"structure,":[126],"though":[127],"they":[128],"not":[130],"appear":[131],"show":[133],"sharp":[135],"structure":[139],"is":[141],"found":[142],"in":[143],"human":[144],"processing":[145],"reflexive":[147],"anaphora.":[148]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":45},{"year":2022,"cited_by_count":34},{"year":2021,"cited_by_count":82},{"year":2020,"cited_by_count":60},{"year":2019,"cited_by_count":8}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}