{"id":"https://openalex.org/W7214748702","doi":"https://doi.org/10.48550/arxiv.2609.34152","title":"Quantitative Measurement of Language Distance among Closely Related Indo-European Languages Using Pretrained Language Models: A Case Study on the North Germanic Branch","display_name":"Quantitative Measurement of Language Distance among Closely Related Indo-European Languages Using Pretrained Language Models: A Case Study on the North Germanic Branch","publication_year":2026,"publication_date":"2026-09-28","ids":{"openalex":"https://openalex.org/W7214748702","doi":"https://doi.org/10.48550/arxiv.2609.34152"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2609.34152","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.34152","pdf_url":"https://arxiv.org/pdf/2609.34152","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2609.34152","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5153503033","display_name":"Yiping Bai","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Bai, Yiping","raw_affiliation_strings":["Guangdong Haiqixing Marine Technology Co., Ltd. , Guangzhou 510000 , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Guangdong Haiqixing Marine Technology Co., Ltd. , Guangzhou 510000 , China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5153503033"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"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":0.6083999872207642,"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":0.6083999872207642,"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":0.36820000410079956,"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/T12377","display_name":"Digital Humanities and Scholarship","score":0.003800000064074993,"subfield":{"id":"https://openalex.org/subfields/1208","display_name":"Literature and Literary Theory"},"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/linguistic-distance","display_name":"linguistic distance","score":0.9829999804496765},{"id":"https://openalex.org/keywords/nordic-languages","display_name":"Scandinavian languages","score":0.8209999799728394},{"id":"https://openalex.org/keywords/danish-language","display_name":"Danish language","score":0.8840000033378601},{"id":"https://openalex.org/keywords/norwegian","display_name":"Norwegian","score":0.6970000267028809},{"id":"https://openalex.org/keywords/swedish-language","display_name":"Swedish language","score":1.0},{"id":"https://openalex.org/keywords/multilingual-pretrained-language-models","display_name":"multilingual pretrained language models","score":0.7519999742507935},{"id":"https://openalex.org/keywords/labse","display_name":"LaBSE","score":0.7850000262260437},{"id":"https://openalex.org/keywords/multilingual-bert","display_name":"multilingual BERT","score":0.9229999780654907},{"id":"https://openalex.org/keywords/semantic-distance","display_name":"semantic distance","score":0.7170000076293945},{"id":"https://openalex.org/keywords/subword-tokenization","display_name":"subword tokenization","score":0.9049999713897705},{"id":"https://openalex.org/keywords/masked-language-modeling","display_name":"masked language modeling","score":0.8730000257492065},{"id":"https://openalex.org/keywords/language-contact","display_name":"language contact","score":0.5180000066757202},{"id":"https://openalex.org/keywords/historical-linguistics","display_name":"historical linguistics","score":0.5870000123977661}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7825999855995178},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6402000188827515},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6175000071525574},{"id":"https://openalex.org/C9679016","wikidata":"https://www.wikidata.org/wiki/Q1417473","display_name":"Principle of maximum entropy","level":2,"score":0.4065999984741211},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.38940000534057617},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.375},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.3684999942779541},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.3440999984741211},{"id":"https://openalex.org/C108154423","wikidata":"https://www.wikidata.org/wiki/Q1469792","display_name":"Salience (neuroscience)","level":2,"score":0.31940001249313354},{"id":"https://openalex.org/C2776306927","wikidata":"https://www.wikidata.org/wiki/Q21200","display_name":"Germanic languages","level":3,"score":0.31869998574256897},{"id":"https://openalex.org/C130318100","wikidata":"https://www.wikidata.org/wiki/Q2268914","display_name":"Semantic similarity","level":2,"score":0.311599999666214},{"id":"https://openalex.org/C176982825","wikidata":"https://www.wikidata.org/wiki/Q835922","display_name":"Lexical analysis","level":2,"score":0.30300000309944153},{"id":"https://openalex.org/C44359876","wikidata":"https://www.wikidata.org/wiki/Q5338467","display_name":"Edit distance","level":2,"score":0.3012999892234802},{"id":"https://openalex.org/C155092808","wikidata":"https://www.wikidata.org/wiki/Q182557","display_name":"Computational linguistics","level":2,"score":0.2896000146865845},{"id":"https://openalex.org/C2776224158","wikidata":"https://www.wikidata.org/wiki/Q187931","display_name":"Phrase","level":2,"score":0.2863999903202057},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.2849000096321106},{"id":"https://openalex.org/C2780762811","wikidata":"https://www.wikidata.org/wiki/Q1784941","display_name":"Cosine similarity","level":3,"score":0.2770000100135803},{"id":"https://openalex.org/C2987487971","wikidata":"https://www.wikidata.org/wiki/Q8096","display_name":"Lexical access","level":3,"score":0.26980000734329224},{"id":"https://openalex.org/C63428231","wikidata":"https://www.wikidata.org/wiki/Q9043","display_name":"Norwegian","level":2,"score":0.26579999923706055},{"id":"https://openalex.org/C129792486","wikidata":"https://www.wikidata.org/wiki/Q1050419","display_name":"Language identification","level":3,"score":0.263700008392334},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.2572000026702881},{"id":"https://openalex.org/C2779804580","wikidata":"https://www.wikidata.org/wiki/Q102047","display_name":"Suffix","level":2,"score":0.25540000200271606},{"id":"https://openalex.org/C2780378701","wikidata":"https://www.wikidata.org/wiki/Q7451195","display_name":"Sentence processing","level":3,"score":0.25519999861717224},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.25440001487731934}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2609.34152","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.34152","pdf_url":"https://arxiv.org/pdf/2609.34152","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2609.34152","doi":"https://doi.org/10.48550/arxiv.2609.34152","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2609.34152","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":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2609.34152","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.34152","pdf_url":"https://arxiv.org/pdf/2609.34152","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[{"score":0.7883062362670898,"id":"https://metadata.un.org/sdg/4","display_name":"Quality education"}],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7214748702.pdf","grobid_xml":"https://content.openalex.org/works/W7214748702.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7221043329","https://openalex.org/W7138849739","https://openalex.org/W2613895792","https://openalex.org/W4416037907","https://openalex.org/W3016943666","https://openalex.org/W7218472872","https://openalex.org/W4324373883","https://openalex.org/W7099518049","https://openalex.org/W2252158196","https://openalex.org/W2343701504"],"abstract_inverted_index":{"Among":[0],"closely":[1,206],"related":[2,207],"North":[3,54],"Germanic":[4,55],"languages,":[5,208],"the":[6,28,52,123,165,191,200,216],"quantification":[7],"of":[8,45,83,172,203,215],"language":[9,46,69,110,218,224],"distance":[10,132,204],"has":[11],"traditionally":[12],"relied":[13],"on":[14,27,51,67,134,190,222],"qualitative":[15],"methods,":[16],"lacking":[17],"a":[18,38,62,195],"unified":[19],"multi-dimensional":[20],"computational":[21,197],"framework.":[22],"Multilingual":[23],"pretrained":[24,68],"models":[25],"based":[26,66],"Transformer":[29],"architecture":[30],"can":[31],"map":[32],"texts":[33],"from":[34,122],"different":[35],"languages":[36],"into":[37],"shared":[39],"vector":[40],"space,":[41],"enabling":[42],"quantitative":[43,64,201],"measurement":[44],"distance.":[47],"This":[48,160],"paper":[49],"focuses":[50],"three":[53,185],"languages---Danish,":[56],"Norwegian":[57],"(Bokm\u00e5l),":[58],"and":[59,80,106,188],"Swedish---and":[60],"proposes":[61],"three-metric":[63],"framework":[65,198],"models:":[70,137],"(1)~sentence-level":[71],"semantic":[72],"distance,":[73],"computed":[74],"as":[75,126],"cosine":[76],"similarity":[77],"between":[78],"LaBSE":[79],"mBERT":[81,113],"encodings":[82],"parallel":[84,99,119],"sentences;":[85],"(2)~orthographic":[86],"fragmentation":[87],"rate,":[88],"measuring":[89],"subword":[90],"tokenization":[91],"efficiency":[92],"when":[93],"cross-applying":[94],"monolingual":[95],"BERT":[96],"vocabularies":[97],"to":[98,179,212],"texts;":[100],"(3)~MLM":[101],"predictability,":[102],"comparing":[103],"prediction":[104],"confidence":[105],"entropy":[107],"in":[108,210],"masked":[109],"modeling":[111],"using":[112],"across":[114],"languages.":[115],"Using":[116],"150":[117],"trilingual":[118],"sentence":[120],"triplets":[121],"Tatoeba":[124],"corpus":[125],"controlled":[127],"samples,":[128],"we":[129],"obtain":[130],"consistent":[131,163],"rankings":[133],"two":[135],"independent":[136],"LaBSE:":[138],"da--no":[139,150],"$0.012":[140],"<":[141,145,152],"$":[142,146,153,157],"no--sv":[143,154],"$0.016":[144,151],"da--sv":[147,158],"$0.020$;":[148],"mBERT:":[149],"$0.045":[155],"\\approx":[156],"$0.046$.":[159],"ranking":[161],"is":[162],"with":[164],"historical":[166],"linguistic":[167],"conclusion":[168],"that":[169],"``400":[170],"years":[171],"Danish":[173],"rule":[174],"over":[175],"Norway":[176],"(1380--1814)":[177],"led":[178],"highly":[180],"cognate":[181],"written":[182],"languages.''":[183],"The":[184],"metrics---semantic,":[186],"orthographic,":[187],"predictability---converge":[189],"same":[192],"conclusion,":[193],"providing":[194],"reproducible":[196],"for":[199],"study":[202],"among":[205],"extensible":[209],"principle":[211],"more":[213],"branches":[214],"Indo-European":[217],"family,":[219],"pending":[220],"validation":[221],"additional":[223],"groups.":[225]},"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2026-09-30T00:00:00"}