{"id":"https://openalex.org/W2985620815","doi":"https://doi.org/10.18653/v1/d19-6106","title":"BERT is Not an Interlingua and the Bias of Tokenization","display_name":"BERT is Not an Interlingua and the Bias of Tokenization","publication_year":2019,"publication_date":"2019-01-01","ids":{"openalex":"https://openalex.org/W2985620815","doi":"https://doi.org/10.18653/v1/d19-6106","mag":"2985620815"},"language":"en","primary_location":{"id":"doi:10.18653/v1/d19-6106","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d19-6106","pdf_url":"https://www.aclweb.org/anthology/D19-6106.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 2nd Workshop on Deep Learning Approaches for Low-Resource NLP (DeepLo 2019)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/D19-6106.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101922999","display_name":"Jasdeep Singh","orcid":"https://orcid.org/0000-0002-6479-4482"},"institutions":[{"id":"https://openalex.org/I4210155268","display_name":"Salesforce (United States)","ror":"https://ror.org/057315g56","country_code":"US","type":"company","lineage":["https://openalex.org/I4210155268"]},{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jasdeep Singh","raw_affiliation_strings":["Stanford University 1 , Salesforce Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stanford University 1 , Salesforce Research","institution_ids":["https://openalex.org/I4210155268","https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008147177","display_name":"Bryan McCann","orcid":"https://orcid.org/0000-0001-9937-1730"},"institutions":[{"id":"https://openalex.org/I4210155268","display_name":"Salesforce (United States)","ror":"https://ror.org/057315g56","country_code":"US","type":"company","lineage":["https://openalex.org/I4210155268"]},{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bryan McCann","raw_affiliation_strings":["Stanford University 1 , Salesforce Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stanford University 1 , Salesforce Research","institution_ids":["https://openalex.org/I4210155268","https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059955534","display_name":"Richard Socher","orcid":"https://orcid.org/0000-0002-3577-639X"},"institutions":[{"id":"https://openalex.org/I4210155268","display_name":"Salesforce (United States)","ror":"https://ror.org/057315g56","country_code":"US","type":"company","lineage":["https://openalex.org/I4210155268"]},{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Richard Socher","raw_affiliation_strings":["Stanford University 1 , Salesforce Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stanford University 1 , Salesforce Research","institution_ids":["https://openalex.org/I4210155268","https://openalex.org/I97018004"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032046813","display_name":"Caiming Xiong","orcid":"https://orcid.org/0000-0003-0349-8628"},"institutions":[{"id":"https://openalex.org/I4210155268","display_name":"Salesforce (United States)","ror":"https://ror.org/057315g56","country_code":"US","type":"company","lineage":["https://openalex.org/I4210155268"]},{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Caiming Xiong","raw_affiliation_strings":["Stanford University 1 , Salesforce Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stanford University 1 , Salesforce Research","institution_ids":["https://openalex.org/I4210155268","https://openalex.org/I97018004"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":6.7965,"has_fulltext":true,"cited_by_count":70,"citation_normalized_percentile":{"value":0.97429457,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"47","last_page":"55"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9993000030517578,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9993000030517578,"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/T12090","display_name":"Language and cultural evolution","score":0.9983999729156494,"subfield":{"id":"https://openalex.org/subfields/3316","display_name":"Cultural Studies"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9976999759674072,"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/lexical-analysis","display_name":"Lexical analysis","score":0.8452677130699158},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8221938610076904},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6910392045974731},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6508390307426453},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.5653777122497559},{"id":"https://openalex.org/keywords/character","display_name":"Character (mathematics)","score":0.5101745128631592},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5088458061218262},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.47807884216308594},{"id":"https://openalex.org/keywords/tree","display_name":"Tree (set theory)","score":0.4431937336921692},{"id":"https://openalex.org/keywords/linguistic-universal","display_name":"Linguistic universal","score":0.4231293201446533},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.27496278285980225},{"id":"https://openalex.org/keywords/theoretical-linguistics","display_name":"Theoretical linguistics","score":0.12175607681274414},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08747744560241699}],"concepts":[{"id":"https://openalex.org/C176982825","wikidata":"https://www.wikidata.org/wiki/Q835922","display_name":"Lexical analysis","level":2,"score":0.8452677130699158},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8221938610076904},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6910392045974731},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6508390307426453},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5653777122497559},{"id":"https://openalex.org/C2780861071","wikidata":"https://www.wikidata.org/wiki/Q1062934","display_name":"Character (mathematics)","level":2,"score":0.5101745128631592},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5088458061218262},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.47807884216308594},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.4431937336921692},{"id":"https://openalex.org/C79078291","wikidata":"https://www.wikidata.org/wiki/Q980142","display_name":"Linguistic universal","level":3,"score":0.4231293201446533},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.27496278285980225},{"id":"https://openalex.org/C153578388","wikidata":"https://www.wikidata.org/wiki/Q351625","display_name":"Theoretical linguistics","level":2,"score":0.12175607681274414},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08747744560241699},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/d19-6106","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d19-6106","pdf_url":"https://www.aclweb.org/anthology/D19-6106.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 2nd Workshop on Deep Learning Approaches for Low-Resource NLP (DeepLo 2019)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/d19-6106","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d19-6106","pdf_url":"https://www.aclweb.org/anthology/D19-6106.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 2nd Workshop on Deep Learning Approaches for Low-Resource NLP (DeepLo 2019)","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.4399999976158142,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2985620815.pdf","grobid_xml":"https://content.openalex.org/works/W2985620815.grobid-xml"},"referenced_works_count":40,"referenced_works":["https://openalex.org/W342285082","https://openalex.org/W1828724394","https://openalex.org/W2025341678","https://openalex.org/W2118090838","https://openalex.org/W2126725946","https://openalex.org/W2142074148","https://openalex.org/W2153579005","https://openalex.org/W2229908198","https://openalex.org/W2250539671","https://openalex.org/W2251033195","https://openalex.org/W2251765408","https://openalex.org/W2251939518","https://openalex.org/W2550821151","https://openalex.org/W2767204723","https://openalex.org/W2891555348","https://openalex.org/W2896457183","https://openalex.org/W2914120296","https://openalex.org/W2923014074","https://openalex.org/W2948017315","https://openalex.org/W2950976310","https://openalex.org/W2952037945","https://openalex.org/W2962739339","https://openalex.org/W2962784628","https://openalex.org/W2963118869","https://openalex.org/W2963310665","https://openalex.org/W2963341956","https://openalex.org/W2963748441","https://openalex.org/W2963756346","https://openalex.org/W2963759780","https://openalex.org/W2963846996","https://openalex.org/W2964266061","https://openalex.org/W2964303116","https://openalex.org/W2970316683","https://openalex.org/W3102226577","https://openalex.org/W4249992252","https://openalex.org/W4294103325","https://openalex.org/W4294170691","https://openalex.org/W4297730150","https://openalex.org/W4299579390","https://openalex.org/W4302343710"],"related_works":["https://openalex.org/W4386014872","https://openalex.org/W4361193986","https://openalex.org/W1847536016","https://openalex.org/W3149094754","https://openalex.org/W3172681236","https://openalex.org/W2148703997","https://openalex.org/W4366851046","https://openalex.org/W2033371749","https://openalex.org/W3214032513","https://openalex.org/W4380568733"],"abstract_inverted_index":{"Multilingual":[0],"transfer":[1],"learning":[2],"can":[3],"benefit":[4],"both":[5],"high-and":[6],"low-resource":[7],"languages,":[8],"but":[9],"the":[10,24,35,59,74,86,114],"source":[11],"of":[12,23,27,113],"these":[13],"improvements":[14],"is":[15,52],"not":[16,62],"well":[17],"understood.":[18],"Cananical":[19],"Correlation":[20],"Analysis":[21],"(CCA)":[22],"internal":[25],"representations":[26,38],"a":[28,45,81,99,111],"pretrained,":[29],"multilingual":[30,131],"BERT":[31,97],"model":[32,36,60],"reveals":[33,80],"that":[34,58,84],"partitions":[37],"for":[39],"each":[40],"language":[41],"rather":[42],"than":[43,105],"using":[44],"common,":[46],"shared,":[47],"interlingual":[48],"space.":[49],"This":[50],"effect":[51],"magnified":[53],"at":[54,123],"deeper":[55],"layers,":[56],"suggesting":[57],"does":[61],"progressively":[63],"abstract":[64],"semantic":[65],"content":[66],"while":[67],"disregarding":[68],"languages.":[69],"Hierarchical":[70],"clustering":[71],"based":[72],"on":[73],"CCA":[75],"similarity":[76],"scores":[77],"between":[78],"languages":[79,122],"tree":[82],"structure":[83,104],"mirrors":[85],"phylogenetic":[87],"trees":[88],"hand-designed":[89],"by":[90,96],"linguists.":[91],"The":[92],"subword":[93],"tokenization":[94],"employed":[95],"provides":[98],"stronger":[100],"bias":[101],"towards":[102],"such":[103],"character-and":[106],"wordlevel":[107],"tokenizations.":[108],"We":[109],"release":[110],"subset":[112],"XNLI":[115],"dataset":[116],"translated":[117],"into":[118,130],"an":[119],"additional":[120],"14":[121],"https://www.github.":[124],"com/salesforce/xnli_extension":[125],"to":[126],"assist":[127],"further":[128],"research":[129],"representations.":[132]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":14},{"year":2022,"cited_by_count":16},{"year":2021,"cited_by_count":13},{"year":2020,"cited_by_count":18}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}