{"id":"https://openalex.org/W4401042004","doi":"https://doi.org/10.18653/v1/2024.vardial-1.6","title":"Modeling Orthographic Variation in Occitan\u2019s Dialects","display_name":"Modeling Orthographic Variation in Occitan\u2019s Dialects","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4401042004","doi":"https://doi.org/10.18653/v1/2024.vardial-1.6"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2024.vardial-1.6","is_oa":true,"landing_page_url":"http://dx.doi.org/10.18653/v1/2024.vardial-1.6","pdf_url":"https://aclanthology.org/2024.vardial-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":"Proceedings of the Eleventh Workshop on NLP for Similar Languages, Varieties, and Dialects (VarDial 2024)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2024.vardial-1.6.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5105911585","display_name":"Zachary Hopton","orcid":null},"institutions":[{"id":"https://openalex.org/I200744771","display_name":"ZHAW Zurich University of Applied Sciences","ror":null,"country_code":"CH","type":null,"lineage":["https://openalex.org/I200744771"]}],"countries":["CH"],"is_corresponding":true,"raw_author_name":"Zachary Hopton","raw_affiliation_strings":["Language and Space Lab University of Zurich Department of Computational Linguistics University of Zurich"],"affiliations":[{"raw_affiliation_string":"Language and Space Lab University of Zurich Department of Computational Linguistics University of Zurich","institution_ids":["https://openalex.org/I200744771"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5047249362","display_name":"No\u00ebmi Aepli","orcid":null},"institutions":[{"id":"https://openalex.org/I200744771","display_name":"ZHAW Zurich University of Applied Sciences","ror":null,"country_code":"CH","type":null,"lineage":["https://openalex.org/I200744771"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"No\u00ebmi Aepli","raw_affiliation_strings":["Language and Space Lab University of Zurich Department of Computational Linguistics University of Zurich"],"affiliations":[{"raw_affiliation_string":"Language and Space Lab University of Zurich Department of Computational Linguistics University of Zurich","institution_ids":["https://openalex.org/I200744771"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5105911585"],"corresponding_institution_ids":["https://openalex.org/I200744771"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.19487434,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"78","last_page":"88"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T14021","display_name":"Medieval European Literature and History","score":0.9986000061035156,"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/T14021","display_name":"Medieval European Literature and History","score":0.9986000061035156,"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/T14489","display_name":"Basque language and culture studies","score":0.9832000136375427,"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/T11640","display_name":"Linguistic Variation and Morphology","score":0.9473999738693237,"subfield":{"id":"https://openalex.org/subfields/3310","display_name":"Linguistics and Language"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/variation","display_name":"Variation (astronomy)","score":0.8360300064086914},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5702790021896362},{"id":"https://openalex.org/keywords/orthographic-projection","display_name":"Orthographic projection","score":0.5672088861465454},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4454951584339142},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.38904276490211487},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3554101586341858},{"id":"https://openalex.org/keywords/astronomy","display_name":"Astronomy","score":0.09580671787261963},{"id":"https://openalex.org/keywords/philosophy","display_name":"Philosophy","score":0.08444884419441223},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.07565829157829285}],"concepts":[{"id":"https://openalex.org/C2778334786","wikidata":"https://www.wikidata.org/wiki/Q1586270","display_name":"Variation (astronomy)","level":2,"score":0.8360300064086914},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5702790021896362},{"id":"https://openalex.org/C175694140","wikidata":"https://www.wikidata.org/wiki/Q980329","display_name":"Orthographic projection","level":2,"score":0.5672088861465454},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4454951584339142},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.38904276490211487},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3554101586341858},{"id":"https://openalex.org/C1276947","wikidata":"https://www.wikidata.org/wiki/Q333","display_name":"Astronomy","level":1,"score":0.09580671787261963},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.08444884419441223},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.07565829157829285}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2024.vardial-1.6","is_oa":true,"landing_page_url":"http://dx.doi.org/10.18653/v1/2024.vardial-1.6","pdf_url":"https://aclanthology.org/2024.vardial-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":"Proceedings of the Eleventh Workshop on NLP for Similar Languages, Varieties, and Dialects (VarDial 2024)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2024.vardial-1.6","is_oa":true,"landing_page_url":"http://dx.doi.org/10.18653/v1/2024.vardial-1.6","pdf_url":"https://aclanthology.org/2024.vardial-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":"Proceedings of the Eleventh Workshop on NLP for Similar Languages, Varieties, and Dialects (VarDial 2024)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G7444390329","display_name":"Sustainable Natural Language Processing for Low-Resource Language Variations","funder_award_id":"191934","funder_id":"https://openalex.org/F4320320924","funder_display_name":"Schweizerischer Nationalfonds zur F\u00f6rderung der Wissenschaftlichen Forschung"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320320924","display_name":"Schweizerischer Nationalfonds zur F\u00f6rderung der Wissenschaftlichen Forschung","ror":"https://ror.org/00yjd3n13"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4401042004.pdf","grobid_xml":"https://content.openalex.org/works/W4401042004.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2386430105","https://openalex.org/W2356521405","https://openalex.org/W2038534795","https://openalex.org/W2384358604","https://openalex.org/W1567829292","https://openalex.org/W3001063351","https://openalex.org/W3196905815","https://openalex.org/W2351370765","https://openalex.org/W3133811809","https://openalex.org/W3204019825"],"abstract_inverted_index":{"Effectively":[0],"normalizing":[1],"textual":[2],"data":[3,24,93],"poses":[4],"a":[5,20,31,47,95],"considerable":[6],"challenge,":[7],"especially":[8],"for":[9,73,107],"lowresource":[10],"languages":[11],"lacking":[12],"standardized":[13],"writing":[14],"systems.In":[15],"this":[16],"study,":[17],"we":[18,45],"fine-tuned":[19,72],"multilingual":[21,102],"model":[22,69],"with":[23],"from":[25,94],"several":[26],"Occitan":[27,52],"dialects":[28,65],"and":[29,76],"conducted":[30],"series":[32],"of":[33,40,55],"experiments":[34],"to":[35,84],"assess":[36],"the":[37,56,64,68,105],"model's":[38,57],"representations":[39],"these":[41],"dialects.For":[42],"evaluation":[43],"purposes,":[44],"compiled":[46],"parallel":[48],"lexicon":[49],"encompassing":[50],"four":[51],"dialects.Intrinsic":[53],"evaluations":[54],"embeddings":[58],"revealed":[59],"that":[60,100],"surface":[61],"similarity":[62],"between":[63],"strengthened":[66],"representations.When":[67],"was":[70,82],"further":[71],"partof-speech":[74],"tagging":[75],"Universal":[77],"Dependency":[78],"parsing,":[79],"its":[80],"performance":[81],"robust":[83],"dialectical":[85],"variation,":[86],"even":[87],"when":[88],"trained":[89],"solely":[90],"on":[91],"part-of-speech":[92],"single":[96],"dialect.Our":[97],"findings":[98],"suggest":[99],"large":[101],"models":[103],"minimize":[104],"need":[106],"spelling":[108],"normalization":[109],"during":[110],"pre-processing.":[111]},"counts_by_year":[],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2025-10-10T00:00:00"}
