{"id":"https://openalex.org/W7140134857","doi":"https://doi.org/10.18653/v1/2026.lchange-1.6","title":"Using Correspondence Patterns to Identify Irregular Words in Cognate Sets Through Leave-One-Out Validation","display_name":"Using Correspondence Patterns to Identify Irregular Words in Cognate Sets Through Leave-One-Out Validation","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7140134857","doi":"https://doi.org/10.18653/v1/2026.lchange-1.6"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2026.lchange-1.6","doi":"https://doi.org/10.18653/v1/2026.lchange-1.6","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.lchange-1.6","pdf_url":"https://aclanthology.org/2026.lchange-1.6.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":"The Proceedings for the 6th International Workshop on Computational Approaches to Language Change (LChange\u201926)","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2026.lchange-1.6.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5019466534","display_name":"Frederic Blum","orcid":"https://orcid.org/0000-0002-2936-0275","observed_orcids":["https://orcid.org/0000-0002-2936-0275"]},"institutions":[{"id":"https://openalex.org/I186354981","display_name":"University of Passau","ror":"https://ror.org/05ydjnb78","country_code":"DE","type":"education","lineage":["https://openalex.org/I186354981"]},{"id":"https://openalex.org/I4210118560","display_name":"Max Planck Institute for Evolutionary Anthropology","ror":"https://ror.org/02a33b393","country_code":"DE","type":"facility","lineage":["https://openalex.org/I149899117","https://openalex.org/I4210118560"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Frederic Blum","raw_affiliation_strings":["Chair for Multilingual Computerlinguistics , University of Passau , Passau , Germany","Department of Linguistic and Cultural Evolution , Max Planck Institute for Evolutionary Anthropology , Leipzig , Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chair for Multilingual Computerlinguistics , University of Passau , Passau , Germany","institution_ids":["https://openalex.org/I186354981"]},{"raw_affiliation_string":"Department of Linguistic and Cultural Evolution , Max Planck Institute for Evolutionary Anthropology , Leipzig , Germany","institution_ids":["https://openalex.org/I4210118560"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5012676548","display_name":"Johann\u2010Mattis List","orcid":"https://orcid.org/0000-0003-2133-8919","observed_orcids":["https://orcid.org/0000-0003-2133-8919"]},"institutions":[{"id":"https://openalex.org/I186354981","display_name":"University of Passau","ror":"https://ror.org/05ydjnb78","country_code":"DE","type":"education","lineage":["https://openalex.org/I186354981"]},{"id":"https://openalex.org/I4210118560","display_name":"Max Planck Institute for Evolutionary Anthropology","ror":"https://ror.org/02a33b393","country_code":"DE","type":"facility","lineage":["https://openalex.org/I149899117","https://openalex.org/I4210118560"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Johann-Mattis List","raw_affiliation_strings":["Chair for Multilingual Computerlinguistics , University of Passau , Passau , Germany","Department of Linguistic and Cultural Evolution , Max Planck Institute for Evolutionary Anthropology , Leipzig , Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chair for Multilingual Computerlinguistics , University of Passau , Passau , Germany","institution_ids":["https://openalex.org/I186354981"]},{"raw_affiliation_string":"Department of Linguistic and Cultural Evolution , Max Planck Institute for Evolutionary Anthropology , Leipzig , Germany","institution_ids":["https://openalex.org/I4210118560"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.0,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"75","last_page":"86"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12768","display_name":"Linguistics and language evolution","score":0.9096999764442444,"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"}},"topics":[{"id":"https://openalex.org/T12768","display_name":"Linguistics and language evolution","score":0.9096999764442444,"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"}},{"id":"https://openalex.org/T12377","display_name":"Digital Humanities and Scholarship","score":0.05700000002980232,"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"}},{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.009700000286102295,"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/sound-correspondences","display_name":"sound correspondences","score":0.8759999871253967},{"id":"https://openalex.org/keywords/cognate-sets","display_name":"cognate sets","score":0.8159999847412109},{"id":"https://openalex.org/keywords/irregular-words","display_name":"irregular words","score":0.8989999890327454},{"id":"https://openalex.org/keywords/leave-one-out-cross-validation","display_name":"leave-one-out cross-validation","score":0.8460000157356262}],"concepts":[{"id":"https://openalex.org/C2777392089","wikidata":"https://www.wikidata.org/wiki/Q690548","display_name":"Cognate","level":2,"score":0.6919999718666077},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5444999933242798},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5169000029563904},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3409000039100647},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.33660000562667847},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.3125},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.25279998779296875},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.24420000612735748},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.24320000410079956},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.24009999632835388}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.18653/v1/2026.lchange-1.6","doi":"https://doi.org/10.18653/v1/2026.lchange-1.6","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.lchange-1.6","pdf_url":"https://aclanthology.org/2026.lchange-1.6.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":"The Proceedings for the 6th International Workshop on Computational Approaches to Language Change (LChange\u201926)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2602.02221","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2602.02221","pdf_url":"https://arxiv.org/pdf/2602.02221","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-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:pure.mpg.de:item_3702528","doi":null,"is_oa":false,"landing_page_url":"https://hdl.handle.net/21.11116/0000-0012-DADD-E","pdf_url":null,"source":{"id":"https://openalex.org/S4306400654","display_name":"MPG.PuRe (Max Planck Society)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I149899117","host_organization_name":"Max Planck Society","host_organization_lineage":["https://openalex.org/I149899117"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"The Proceedings for the 6th International Workshop on Computational Approaches to Language Change (LC}hange{'26)","raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"doi:10.48550/arxiv.2602.02221","doi":"https://doi.org/10.48550/arxiv.2602.02221","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2602.02221","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":"doi:10.18653/v1/2026.lchange-1.6","doi":"https://doi.org/10.18653/v1/2026.lchange-1.6","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.lchange-1.6","pdf_url":"https://aclanthology.org/2026.lchange-1.6.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":"The Proceedings for the 6th International Workshop on Computational Approaches to Language Change (LChange\u201926)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G8513461425","display_name":null,"funder_award_id":"CALC3","funder_id":"https://openalex.org/F4320322434","funder_display_name":"Max-Planck-Gesellschaft"}],"funders":[{"id":"https://openalex.org/F4320322434","display_name":"Max-Planck-Gesellschaft","ror":"https://ror.org/01hhn8329"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7140134857.pdf","grobid_xml":"https://content.openalex.org/works/W7140134857.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7097983241","https://openalex.org/W1518614801","https://openalex.org/W4386576655","https://openalex.org/W2581563496","https://openalex.org/W7172581699","https://openalex.org/W2979390785","https://openalex.org/W7099860572","https://openalex.org/W7101143985","https://openalex.org/W2812783770","https://openalex.org/W1969084528"],"abstract_inverted_index":{"Regular":[0],"sound":[1],"correspondences":[2],"constitute":[3],"the":[4,11,35,38,48,71,108,118,126,149,152,162,170,184,190,199,218],"principal":[5],"evidence":[6],"in":[7,44,131,183,216,225],"historical":[8,45],"language":[9,227],"comparison.Despite":[10],"heuristic":[12],"focus":[13],"on":[14,165,189,205],"regularity,":[15],"it":[16],"is":[17,29],"often":[18],"more":[19,30],"an":[20,140,156,213],"intuitive":[21],"judgement":[22],"than":[23,32],"a":[24,66,79,86],"quantified":[25],"evaluation,":[26],"and":[27,47,63,115,179,198,222],"irregularity":[28,182],"common":[31],"expected":[33],"from":[34],"Neogrammarian":[36],"model.Given":[37],"recent":[39],"progress":[40],"of":[41,51,75,82,128,159,172,176,193,220],"computational":[42,88],"methods":[43],"linguistics":[46],"increased":[49],"availability":[50],"standardized":[52],"lexical":[53],"data,":[54],"we":[55,69,120,207],"are":[56],"now":[57],"able":[58],"to":[59,94,103,124],"improve":[60],"our":[61,146,187,194],"workflows":[62],"provide":[64],"such":[65],"quantitative":[67],"evaluation.Here,":[68],"present":[70,85],"balanced":[72],"average":[73],"recurrence":[74],"correspondence":[76,105],"patterns":[77],"as":[78],"new":[80,87,195],"measure":[81,93,125,197],"regularity.We":[83],"also":[84,168],"method":[89,109,147,154,203],"that":[90,98,209],"uses":[91],"this":[92],"identify":[95],"cognate":[96,129,201],"sets":[97,130],"lack":[99],"regularity":[100,127,196],"with":[101,161,174],"respect":[102],"their":[104],"patterns.We":[106],"validate":[107],"through":[110],"two":[111],"experiments,":[112,119],"using":[113],"simulated":[114],"real":[116,166],"data.In":[117],"employ":[121],"leave-one-out":[122],"validation":[123],"which":[132],"one":[133],"word":[134],"form":[135],"has":[136],"been":[137],"replaced":[138],"by":[139],"irregular":[141,200],"one,":[142],"checking":[143],"how":[144,180],"well":[145],"identifies":[148],"forms":[150],"causing":[151],"irregularity.Our":[153],"achieves":[155],"overall":[157],"accuracy":[158],"85%":[160],"datasets":[163,178,224],"based":[164,204],"data.We":[167],"show":[169],"benefits":[171],"working":[173],"subsamples":[175],"large":[177],"increasing":[181],"data":[185],"influences":[186],"results.Reflecting":[188],"broader":[191],"potential":[192],"identification":[202],"it,":[206],"conclude":[208],"they":[210],"could":[211],"play":[212],"important":[214],"role":[215],"improving":[217],"quality":[219],"existing":[221],"future":[223],"computer-assisted":[226],"comparison.":[228]},"counts_by_year":[],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2026-02-06T00:00:00"}