{"id":"https://openalex.org/W7140125961","doi":"https://doi.org/10.18653/v1/2026.vardial-1.18","title":"How Should We Model the Probability of a Language?","display_name":"How Should We Model the Probability of a Language?","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7140125961","doi":"https://doi.org/10.18653/v1/2026.vardial-1.18"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2026.vardial-1.18","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.vardial-1.18","pdf_url":"https://aclanthology.org/2026.vardial-1.18.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 13th Workshop on NLP for Similar Languages, Varieties and Dialects","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2026.vardial-1.18.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Rasul Dent","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rasul Dent","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Pedro Ortiz Suarez","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pedro Ortiz Suarez","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Thibault Cl\u00e9rice","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Thibault Cl\u00e9rice","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"Beno\u00eet Sagot","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Beno\u00eet Sagot","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"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":0.39345837,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"223","last_page":"233"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12090","display_name":"Language and cultural evolution","score":0.15230000019073486,"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"}},"topics":[{"id":"https://openalex.org/T12090","display_name":"Language and cultural evolution","score":0.15230000019073486,"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/T10034","display_name":"Syntax, Semantics, Linguistic Variation","score":0.06210000067949295,"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/T12380","display_name":"Authorship Attribution and Profiling","score":0.051100000739097595,"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/framing","display_name":"Framing (construction)","score":0.6388999819755554},{"id":"https://openalex.org/keywords/incentive","display_name":"Incentive","score":0.45339998602867126},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.34060001373291016},{"id":"https://openalex.org/keywords/position","display_name":"Position (finance)","score":0.31200000643730164},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.3075999915599823}],"concepts":[{"id":"https://openalex.org/C169087156","wikidata":"https://www.wikidata.org/wiki/Q2131593","display_name":"Framing (construction)","level":2,"score":0.6388999819755554},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5712000131607056},{"id":"https://openalex.org/C29122968","wikidata":"https://www.wikidata.org/wiki/Q1414816","display_name":"Incentive","level":2,"score":0.45339998602867126},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3411000072956085},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.34060001373291016},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.33629998564720154},{"id":"https://openalex.org/C198082294","wikidata":"https://www.wikidata.org/wiki/Q3399648","display_name":"Position (finance)","level":2,"score":0.31200000643730164},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.3075999915599823},{"id":"https://openalex.org/C2909318450","wikidata":"https://www.wikidata.org/wiki/Q15222032","display_name":"Unbiased Estimation","level":3,"score":0.26019999384880066},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.25780001282691956}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.vardial-1.18","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.vardial-1.18","pdf_url":"https://aclanthology.org/2026.vardial-1.18.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 13th Workshop on NLP for Similar Languages, Varieties and Dialects","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.vardial-1.18","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.vardial-1.18","pdf_url":"https://aclanthology.org/2026.vardial-1.18.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 13th Workshop on NLP for Similar Languages, Varieties and Dialects","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7140125961.pdf","grobid_xml":"https://content.openalex.org/works/W7140125961.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Of":[0],"the":[1,7,63],"over":[2],"7,000":[3],"languages":[4,33,87,105],"spoken":[5],"in":[6,20],"world,":[8],"commercial":[9],"language":[10],"identification":[11],"(LID)":[12],"systems":[13,23],"only":[14],"reliably":[15],"identify":[16],"a":[17,52,92],"few":[18],"hundred":[19],"written":[21],"form.Research-grade":[22],"extend":[24],"this":[25,43],"coverage":[26,34,84],"under":[27],"certain":[28],"circumstances,":[29],"but":[30],"for":[31,85],"most":[32],"remains":[35],"patchy":[36],"or":[37],"nonexistent.This":[38],"position":[39],"paper":[40],"argues":[41],"that":[42,76,82,103],"situation":[44],"is":[45,71],"largely":[46],"selfimposed.In":[47],"particular,":[48],"it":[49],"arises":[50],"from":[51],"persistent":[53],"framing":[54],"of":[55,66],"LID":[56,90],"as":[57,91],"decontextualized":[58],"text":[59],"classification,":[60],"which":[61],"obscures":[62],"central":[64],"role":[65],"prior":[67],"probability":[68],"estimation":[69],"and":[70,95],"reinforced":[72],"by":[73],"institutional":[74],"incentives":[75],"favor":[77],"global,":[78],"fixed-prior":[79],"models.We":[80],"argue":[81],"improving":[83],"tail":[86],"requires":[88],"rethinking":[89],"routing":[93],"problem":[94],"developing":[96],"principled":[97],"ways":[98],"to":[99],"incorporate":[100],"environmental":[101],"cues":[102],"make":[104],"locally":[106],"plausible.":[107]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-02-12T00:00:00"}