{"id":"https://openalex.org/W4401042534","doi":"https://doi.org/10.18653/v1/2024.vardial-1.12","title":"Experiments in Multi-Variant Natural Language Processing for Nahuatl","display_name":"Experiments in Multi-Variant Natural Language Processing for Nahuatl","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4401042534","doi":"https://doi.org/10.18653/v1/2024.vardial-1.12"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2024.vardial-1.12","is_oa":true,"landing_page_url":"http://dx.doi.org/10.18653/v1/2024.vardial-1.12","pdf_url":"https://aclanthology.org/2024.vardial-1.12.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-1.12.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5063307617","display_name":"Robert Pugh","orcid":null},"institutions":[{"id":"https://openalex.org/I4210119109","display_name":"Indiana University Bloomington","ror":"https://ror.org/02k40bc56","country_code":"US","type":"education","lineage":["https://openalex.org/I4210119109","https://openalex.org/I592451"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Robert Pugh","raw_affiliation_strings":["Indiana University , Bloomington Department of Linguistics"],"affiliations":[{"raw_affiliation_string":"Indiana University , Bloomington Department of Linguistics","institution_ids":["https://openalex.org/I4210119109"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5076604380","display_name":"Francis M. Tyers","orcid":"https://orcid.org/0000-0001-6108-2220"},"institutions":[{"id":"https://openalex.org/I4210119109","display_name":"Indiana University Bloomington","ror":"https://ror.org/02k40bc56","country_code":"US","type":"education","lineage":["https://openalex.org/I4210119109","https://openalex.org/I592451"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Francis Tyers","raw_affiliation_strings":["Indiana University , Bloomington Department of Linguistics"],"affiliations":[{"raw_affiliation_string":"Indiana University , Bloomington Department of Linguistics","institution_ids":["https://openalex.org/I4210119109"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5063307617"],"corresponding_institution_ids":["https://openalex.org/I4210119109"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.097764,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"140","last_page":"151"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9832000136375427,"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":0.9832000136375427,"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/nahuatl","display_name":"Nahuatl","score":0.8138681054115295},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7126502990722656},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5781353712081909},{"id":"https://openalex.org/keywords/natural","display_name":"Natural (archaeology)","score":0.500359296798706},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.43351253867149353},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.399664968252182},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.28111642599105835},{"id":"https://openalex.org/keywords/history","display_name":"History","score":0.1529015302658081},{"id":"https://openalex.org/keywords/philosophy","display_name":"Philosophy","score":0.05980631709098816},{"id":"https://openalex.org/keywords/archaeology","display_name":"Archaeology","score":0.053875088691711426}],"concepts":[{"id":"https://openalex.org/C2779025792","wikidata":"https://www.wikidata.org/wiki/Q13300","display_name":"Nahuatl","level":2,"score":0.8138681054115295},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7126502990722656},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5781353712081909},{"id":"https://openalex.org/C2776608160","wikidata":"https://www.wikidata.org/wiki/Q4785462","display_name":"Natural (archaeology)","level":2,"score":0.500359296798706},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.43351253867149353},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.399664968252182},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.28111642599105835},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.1529015302658081},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.05980631709098816},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.053875088691711426}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2024.vardial-1.12","is_oa":true,"landing_page_url":"http://dx.doi.org/10.18653/v1/2024.vardial-1.12","pdf_url":"https://aclanthology.org/2024.vardial-1.12.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-1.12","is_oa":true,"landing_page_url":"http://dx.doi.org/10.18653/v1/2024.vardial-1.12","pdf_url":"https://aclanthology.org/2024.vardial-1.12.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":[{"score":0.6700000166893005,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4401042534.pdf","grobid_xml":"https://content.openalex.org/works/W4401042534.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2511051395","https://openalex.org/W2013628744","https://openalex.org/W4327941905","https://openalex.org/W2018923551","https://openalex.org/W186200367","https://openalex.org/W2626056942","https://openalex.org/W3204019825","https://openalex.org/W4226226396","https://openalex.org/W3153750606","https://openalex.org/W4308854837"],"abstract_inverted_index":{"Linguistic":[0],"variation":[1,53],"is":[2,10,107],"a":[3,31,48,87],"complicating":[4],"factor":[5],"for":[6,13,41,66],"digital":[7],"language":[8,39,46],"technologies.This":[9],"particularly":[11],"true":[12],"languages":[14],"that":[15,106],"lack":[16],"an":[17,43],"official":[18],"\"standard\"":[19],"variety,":[20],"including":[21],"many":[22],"regional":[23],"and":[24,54,77,80,95,120],"minoritized":[25],"languages.In":[26],"this":[27],"paper,":[28],"we":[29,70],"describe":[30],"set":[32],"of":[33,51,74,102],"experiments":[34],"focused":[35],"on":[36,86],"multivariant":[37],"natural":[38],"processing":[40],"Nahuatl,":[42],"indigenous":[44],"Mexican":[45],"with":[47],"high":[49],"degree":[50],"linguistic":[52],"no":[55],"single":[56],"recognized":[57],"standard":[58],"variant.Using":[59],"small":[60],"(10k":[61],"tokens),":[62],"recently-published":[63],"annotated":[64],"datasets":[65],"two":[67],"Nahuatl":[68,89],"variants,":[69],"compare":[71],"the":[72,96,118,122],"performance":[73],"single-variant,":[75],"cross-variant,":[76],"joint":[78],"training,":[79],"explore":[81],"how":[82],"different":[83],"models":[84],"perform":[85],"third":[88],"variant,":[90],"unseen":[91],"in":[92],"training.These":[93],"results":[94],"subsequent":[97],"discussion":[98],"contribute":[99],"to":[100,109,116],"efforts":[101],"developing":[103],"low-resource":[104],"NLP":[105],"robust":[108],"diatopic":[110],"variation.We":[111],"share":[112],"all":[113],"code":[114],"used":[115],"process":[117],"data":[119],"run":[121],"experiments.":[123],"1":[124]},"counts_by_year":[],"updated_date":"2026-03-14T06:41:57.775601","created_date":"2025-10-10T00:00:00"}
