{"id":"https://openalex.org/W4416966519","doi":"https://doi.org/10.48550/arxiv.2512.01713","title":"Self-Supervised Borrowing Detection on Multilingual Wordlists","display_name":"Self-Supervised Borrowing Detection on Multilingual Wordlists","publication_year":2025,"publication_date":"2025-12-01","ids":{"openalex":"https://openalex.org/W4416966519","doi":"https://doi.org/10.48550/arxiv.2512.01713"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2512.01713","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2512.01713","pdf_url":"https://arxiv.org/pdf/2512.01713","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","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2512.01713","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5012536145","display_name":"Tim Wientzek","orcid":"https://orcid.org/0000-0001-9375-6381","observed_orcids":["https://orcid.org/0000-0001-9375-6381"]},"institutions":[{"id":"https://openalex.org/I8087733","display_name":"University of T\u00fcbingen","ror":"https://ror.org/03a1kwz48","country_code":"DE","type":"education","lineage":["https://openalex.org/I8087733"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Wientzek, Tim","raw_affiliation_strings":["University of T\u00fcbingen Department of Linguistics Keplerstr. 2 , 72074 T\u00fcbingen , Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of T\u00fcbingen Department of Linguistics Keplerstr. 2 , 72074 T\u00fcbingen , Germany","institution_ids":["https://openalex.org/I8087733"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5012536145"],"corresponding_institution_ids":["https://openalex.org/I8087733"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":1,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.391400009393692,"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":0.391400009393692,"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/T10028","display_name":"Topic Modeling","score":0.2685999870300293,"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/T14006","display_name":"Linguistics, Language Diversity, and Identity","score":0.2125999927520752,"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/self-supervised-learning","display_name":"self-supervised learning","score":0.9509999752044678},{"id":"https://openalex.org/keywords/pointwise-mutual-information","display_name":"pointwise mutual information","score":0.8389999866485596},{"id":"https://openalex.org/keywords/contrastive-learning","display_name":"contrastive learning","score":0.9750000238418579},{"id":"https://openalex.org/keywords/string-similarity","display_name":"string similarity","score":0.5450000166893005},{"id":"https://openalex.org/keywords/decision-threshold-selection","display_name":"decision threshold selection","score":0.746999979019165},{"id":"https://openalex.org/keywords/character-encoding","display_name":"character encoding","score":0.656000018119812},{"id":"https://openalex.org/keywords/temperature-settings","display_name":"setting temperature","score":0.5329999923706055},{"id":"https://openalex.org/keywords/data-augmentation","display_name":"data augmentation","score":0.824999988079071}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6955999732017517},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6442999839782715},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6191999912261963},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.6187999844551086},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5453000068664551},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.5386999845504761},{"id":"https://openalex.org/C157486923","wikidata":"https://www.wikidata.org/wiki/Q1376436","display_name":"String (physics)","level":2,"score":0.5123000144958496},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5063999891281128},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.38909998536109924},{"id":"https://openalex.org/C2780861071","wikidata":"https://www.wikidata.org/wiki/Q1062934","display_name":"Character (mathematics)","level":2,"score":0.37709999084472656},{"id":"https://openalex.org/C22820288","wikidata":"https://www.wikidata.org/wiki/Q9050568","display_name":"String metric","level":4,"score":0.35850000381469727},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.35370001196861267},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.31209999322891235},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.29829999804496765},{"id":"https://openalex.org/C143271835","wikidata":"https://www.wikidata.org/wiki/Q254515","display_name":"Similitude","level":2,"score":0.28349998593330383},{"id":"https://openalex.org/C59656382","wikidata":"https://www.wikidata.org/wiki/Q191536","display_name":"Conjunction (astronomy)","level":2,"score":0.271699994802475},{"id":"https://openalex.org/C155092808","wikidata":"https://www.wikidata.org/wiki/Q182557","display_name":"Computational linguistics","level":2,"score":0.2599000036716461},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.259799987077713}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2512.01713","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2512.01713","pdf_url":"https://arxiv.org/pdf/2512.01713","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.2512.01713","doi":"https://doi.org/10.48550/arxiv.2512.01713","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2512.01713","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2512.01713","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2512.01713","pdf_url":"https://arxiv.org/pdf/2512.01713","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":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G534521444","display_name":null,"funder_award_id":"DFG-KFG2237","funder_id":"https://openalex.org/F4320320879","funder_display_name":"Deutsche Forschungsgemeinschaft"},{"id":"https://openalex.org/G7258815532","display_name":null,"funder_award_id":"KFG 2237","funder_id":"https://openalex.org/F4320320879","funder_display_name":"Deutsche Forschungsgemeinschaft"}],"funders":[{"id":"https://openalex.org/F4320320879","display_name":"Deutsche Forschungsgemeinschaft","ror":"https://ror.org/018mejw64"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416966519.pdf","grobid_xml":"https://content.openalex.org/works/W4416966519.grobid-xml"},"referenced_works_count":24,"referenced_works":["https://openalex.org/W2055563597","https://openalex.org/W2121186983","https://openalex.org/W2138621090","https://openalex.org/W2139382299","https://openalex.org/W2151614066","https://openalex.org/W2156279557","https://openalex.org/W2575780413","https://openalex.org/W2626778328","https://openalex.org/W2788886867","https://openalex.org/W2908510526","https://openalex.org/W3005680577","https://openalex.org/W3035614721","https://openalex.org/W3081931604","https://openalex.org/W3156636935","https://openalex.org/W3199471803","https://openalex.org/W3201950822","https://openalex.org/W4230213531","https://openalex.org/W4282970993","https://openalex.org/W4283023587","https://openalex.org/W4386566655","https://openalex.org/W4388979610","https://openalex.org/W4407185082","https://openalex.org/W6969173555","https://openalex.org/W6977515017"],"related_works":["https://openalex.org/W6987811343","https://openalex.org/W7077884004","https://openalex.org/W3216514415","https://openalex.org/W7131800953","https://openalex.org/W6906611786","https://openalex.org/W7160206522","https://openalex.org/W4402670762","https://openalex.org/W1498591840","https://openalex.org/W4285212649","https://openalex.org/W7220600186"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"a":[3,24,29,116],"fully":[4],"self-supervised":[5],"approach":[6,101],"to":[7,103,122],"borrowing":[8],"detection":[9],"in":[10],"multilingual":[11],"wordlists.":[12],"The":[13,100],"method":[14],"combines":[15],"two":[16],"sources":[17],"of":[18,92,105],"information:":[19],"PMI":[20,58],"similarities":[21],"based":[22],"on":[23,34,53,78],"global":[25],"correspondence":[26],"model":[27],"and":[28,70,72,97,112],"lightweight":[30],"contrastive":[31],"component":[32],"trained":[33],"phonetic":[35],"feature":[36],"vectors.":[37],"It":[38],"further":[39],"includes":[40],"an":[41],"automatic":[42],"procedure":[43],"for":[44],"selecting":[45],"decision":[46],"thresholds":[47],"without":[48,109],"requiring":[49],"labeled":[50],"data.":[51],"Experiments":[52],"benchmark":[54],"datasets":[55,104],"show":[56],"that":[57,73,119],"alone":[59],"already":[60],"improves":[61],"over":[62],"existing":[63],"string":[64],"similarity":[65,76],"measures":[66],"such":[67],"as":[68],"NED":[69],"SCA,":[71],"the":[74,90],"combined":[75],"performs":[77],"par":[79],"with":[80,115],"or":[81],"better":[82],"than":[83],"supervised":[84],"baselines.":[85],"An":[86],"ablation":[87],"study":[88],"highlights":[89],"importance":[91],"character":[93],"encoding,":[94],"temperature":[95],"settings":[96],"augmentation":[98],"strategies.":[99],"scales":[102],"different":[106],"sizes,":[107],"works":[108],"manual":[110],"supervision":[111],"is":[113],"provided":[114],"command-line":[117],"tool":[118],"allows":[120],"researchers":[121],"conduct":[123],"their":[124],"own":[125],"studies.":[126]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2025-12-03T00:00:00"}