{"id":"https://openalex.org/W3197797121","doi":null,"title":"Establishing Interlingua in Multilingual Language Models.","display_name":"Establishing Interlingua in Multilingual Language Models.","publication_year":2021,"publication_date":"2021-09-02","ids":{"openalex":"https://openalex.org/W3197797121","mag":"3197797121"},"language":"en","primary_location":{"id":"mag:3197797121","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2109.01207","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},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2109.01207","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5020689953","display_name":"Maksym Del","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Maksym Del","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5113712910","display_name":"Mark Fishel","orcid":"https://orcid.org/0000-0003-1932-2600","observed_orcids":["https://orcid.org/0000-0003-1932-2600"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mark Fishel","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9276999831199646,"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":0.9276999831199646,"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":0.052299998700618744,"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":0.006599999964237213,"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/interlingua","display_name":"interlingua","score":0.8109999895095825},{"id":"https://openalex.org/keywords/multilingual-language-models","display_name":"multilingual language models","score":0.9480000138282776},{"id":"https://openalex.org/keywords/bert","display_name":"BERT","score":0.671999990940094},{"id":"https://openalex.org/keywords/multilingual-bert","display_name":"multilingual BERT","score":0.6359999775886536},{"id":"https://openalex.org/keywords/zero-shot-cross-lingual-transfer","display_name":"zero-shot cross-lingual transfer","score":0.9129999876022339},{"id":"https://openalex.org/keywords/sentence-representation","display_name":"sentence representation","score":0.34299999475479126}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7399888634681702},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6429753303527832},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.6097975969314575},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.582764208316803},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5691523551940918},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.5483995079994202},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5297449827194214},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.524367094039917},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.5033003687858582},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.4783453643321991},{"id":"https://openalex.org/C2776818064","wikidata":"https://www.wikidata.org/wiki/Q829903","display_name":"Agreement","level":2,"score":0.4508136212825775},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.14912614226341248},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.11559557914733887},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.08181136846542358},{"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/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","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/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"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/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","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}],"mesh":[],"locations_count":1,"locations":[{"id":"mag:3197797121","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2109.01207","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}],"best_oa_location":{"id":"mag:3197797121","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2109.01207","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},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W2100235303","https://openalex.org/W2767204723","https://openalex.org/W2942810103","https://openalex.org/W2963341956","https://openalex.org/W2963759780","https://openalex.org/W2965373594","https://openalex.org/W2978017171","https://openalex.org/W2983040767","https://openalex.org/W2985620815","https://openalex.org/W3013840636","https://openalex.org/W3015299511","https://openalex.org/W3035547806","https://openalex.org/W3102483398","https://openalex.org/W3122044994"],"related_works":["https://openalex.org/W4312935320","https://openalex.org/W4286989049","https://openalex.org/W4286892373","https://openalex.org/W2985620815","https://openalex.org/W2939455697","https://openalex.org/W2952638691","https://openalex.org/W7211865765","https://openalex.org/W4416045800","https://openalex.org/W4287367800","https://openalex.org/W3200065025"],"abstract_inverted_index":{"Large":[0],"multilingual":[1],"language":[2,74],"models":[3,20],"show":[4,54],"remarkable":[5],"zero-shot":[6],"cross-lingual":[7],"transfer":[8],"performance":[9],"on":[10],"a":[11,28,69,111,124],"range":[12],"of":[13,24,60,88,119],"tasks.":[14],"Follow-up":[15],"works":[16],"hypothesized":[17],"that":[18,47,55,79,106,128],"these":[19],"internally":[21],"project":[22],"representations":[23],"different":[25,63],"languages":[26,64,103,127],"into":[27],"shared":[29,70,136],"interlingual":[30,108],"space.":[31,137],"However,":[32],"they":[33],"produced":[34],"contradictory":[35],"results.":[36],"In":[37],"this":[38,80,150],"paper,":[39],"we":[40,77],"correct":[41],"the":[42,57,107,116,135,147],"famous":[43],"prior":[44],"work":[45],"claiming":[46],"BERT":[48],"is":[49,83,144],"not":[50],"an":[51],"Interlingua":[52],"and":[53,91,104],"with":[56],"proper":[58],"choice":[59],"sentence":[61],"representation":[62],"actually":[65],"do":[66],"converge":[67,133],"to":[68,100,115,130,132,134],"space":[71,109],"in":[72],"such":[73],"models.":[75,94],"Furthermore,":[76],"demonstrate":[78],"convergence":[81],"pattern":[82],"robust":[84],"across":[85],"four":[86],"measures":[87],"correlation":[89],"similarity":[90],"six":[92],"mBERT-like":[93],"We":[95,121],"then":[96],"extend":[97],"our":[98,142],"analysis":[99],"28":[101],"diverse":[102],"find":[105],"exhibits":[110],"particular":[112],"structure":[113],"similar":[114],"linguistic":[117],"relatedness":[118],"languages.":[120],"also":[122],"highlight":[123],"few":[125],"outlier":[126],"seem":[129],"fail":[131],"The":[138],"code":[139],"for":[140],"replicating":[141],"results":[143],"available":[145],"at":[146],"following":[148],"URL:":[149],"https":[151],"URL.":[152]},"counts_by_year":[{"year":2023,"cited_by_count":2}],"updated_date":"2026-10-16T09:59:22.235173","created_date":"2021-09-13T00:00:00"}
