{"id":"https://openalex.org/W4404875321","doi":"https://doi.org/10.1016/j.softx.2024.101985","title":"Automatic grammatical tagger for a Spanish\u2013Mixtec parallel corpus","display_name":"Automatic grammatical tagger for a Spanish\u2013Mixtec parallel corpus","publication_year":2024,"publication_date":"2024-11-29","ids":{"openalex":"https://openalex.org/W4404875321","doi":"https://doi.org/10.1016/j.softx.2024.101985"},"language":"en","primary_location":{"id":"doi:10.1016/j.softx.2024.101985","doi":"https://doi.org/10.1016/j.softx.2024.101985","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.softx.2024.101985","pdf_url":null,"source":{"id":"https://openalex.org/S2506067282","display_name":"SoftwareX","issn_l":"2352-7110","issn":["2352-7110"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["cwts-core","doaj","dongbi-d","jufo-1","ki-jl-1","norway-1","poland-200","vabb-shw"],"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"SoftwareX","raw_type":"journal-article"},"volume":null,"type":"software-paper","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1016/j.softx.2024.101985","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5063702951","display_name":"Hermilo Santiago-Benito","orcid":"https://orcid.org/0000-0001-5650-1240","observed_orcids":["https://orcid.org/0000-0001-5650-1240"]},"institutions":[{"id":"https://openalex.org/I157492648","display_name":"Autonomous University of Queretaro","ror":"https://ror.org/00v8fdc16","country_code":"MX","type":"education","lineage":["https://openalex.org/I157492648"]}],"countries":["MX"],"is_corresponding":false,"raw_author_name":"Hermilo Santiago-Benito","raw_affiliation_strings":["Facultad de Inform\u00e1tica, Universidad Autonoma de Quer\u00e9taro, Av. de las Ciencias S/N, Campus Juriquilla, C.P. 76230, Quer\u00e9taro, Mexico"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Facultad de Inform\u00e1tica, Universidad Autonoma de Quer\u00e9taro, Av. de las Ciencias S/N, Campus Juriquilla, C.P. 76230, Quer\u00e9taro, Mexico","institution_ids":["https://openalex.org/I157492648"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068400798","display_name":"Diana Margarita C\u00f3rdova Esparza","orcid":"https://orcid.org/0000-0002-5657-7752","observed_orcids":["https://orcid.org/0000-0002-5657-7752"]},"institutions":[{"id":"https://openalex.org/I157492648","display_name":"Autonomous University of Queretaro","ror":"https://ror.org/00v8fdc16","country_code":"MX","type":"education","lineage":["https://openalex.org/I157492648"]}],"countries":["MX"],"is_corresponding":true,"raw_author_name":"Diana-Margarita C\u00f3rdova-Esparza","raw_affiliation_strings":["Facultad de Inform\u00e1tica, Universidad Autonoma de Quer\u00e9taro, Av. de las Ciencias S/N, Campus Juriquilla, C.P. 76230, Quer\u00e9taro, Mexico"],"raw_orcid":"https://orcid.org/0000-0002-5657-7752","affiliations":[{"raw_affiliation_string":"Facultad de Inform\u00e1tica, Universidad Autonoma de Quer\u00e9taro, Av. de las Ciencias S/N, Campus Juriquilla, C.P. 76230, Quer\u00e9taro, Mexico","institution_ids":["https://openalex.org/I157492648"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051606070","display_name":"No\u00e9 Alejandro Castro-S\u00e1nchez","orcid":"https://orcid.org/0000-0002-8083-3891","observed_orcids":["https://orcid.org/0000-0002-8083-3891"]},"institutions":[{"id":"https://openalex.org/I4210090124","display_name":"Tecnol\u00f3gico Nacional de M\u00e9xico","ror":"https://ror.org/00davry38","country_code":"MX","type":"government","lineage":["https://openalex.org/I1302736544","https://openalex.org/I4210090124","https://openalex.org/I4405258672"]},{"id":"https://openalex.org/I4210138655","display_name":"Centro Nacional de Investigaci\u00f3n y Desarrollo Tecnol\u00f3gico","ror":"https://ror.org/0314ecq26","country_code":"MX","type":"facility","lineage":["https://openalex.org/I4210138655"]}],"countries":["MX"],"is_corresponding":false,"raw_author_name":"No\u00e9-Alejandro Castro-S\u00e1nchez","raw_affiliation_strings":["Centro Nacional de Investigaci\u00f3n y Desarrollo Tecnol\u00f3gico, Tecnol\u00f3gico Nacional de Mexico, Interior Internado Palmira S/N, Palmira, C.P. 62493, Cuernavaca, Morelos, Mexico"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centro Nacional de Investigaci\u00f3n y Desarrollo Tecnol\u00f3gico, Tecnol\u00f3gico Nacional de Mexico, Interior Internado Palmira S/N, Palmira, C.P. 62493, Cuernavaca, Morelos, Mexico","institution_ids":["https://openalex.org/I4210090124","https://openalex.org/I4210138655"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072558771","display_name":"Juan R. Terven","orcid":"https://orcid.org/0000-0001-6662-0390","observed_orcids":["https://orcid.org/0000-0001-6662-0390"]},"institutions":[{"id":"https://openalex.org/I59361560","display_name":"Instituto Polit\u00e9cnico Nacional","ror":"https://ror.org/059sp8j34","country_code":"MX","type":"education","lineage":["https://openalex.org/I59361560"]}],"countries":["MX"],"is_corresponding":false,"raw_author_name":"Juan Terven","raw_affiliation_strings":["CICATA - Unidad Quer\u00e9taro, Instituto Polit\u00e9cnico Nacional, Cerro Blanco No. 141, Col. Colinas del Cimatario, C.P. 76090, Quer\u00e9taro, Mexico"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CICATA - Unidad Quer\u00e9taro, Instituto Polit\u00e9cnico Nacional, Cerro Blanco No. 141, Col. Colinas del Cimatario, C.P. 76090, Quer\u00e9taro, Mexico","institution_ids":["https://openalex.org/I59361560"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078258282","display_name":"Julio-Alejandro Romero-Gonz\u00e1lez","orcid":"https://orcid.org/0000-0001-7257-7595","observed_orcids":["https://orcid.org/0000-0001-7257-7595"]},"institutions":[{"id":"https://openalex.org/I157492648","display_name":"Autonomous University of Queretaro","ror":"https://ror.org/00v8fdc16","country_code":"MX","type":"education","lineage":["https://openalex.org/I157492648"]}],"countries":["MX"],"is_corresponding":false,"raw_author_name":"Julio-Alejandro Romero-Gonz\u00e1lez","raw_affiliation_strings":["Facultad de Inform\u00e1tica, Universidad Autonoma de Quer\u00e9taro, Av. de las Ciencias S/N, Campus Juriquilla, C.P. 76230, Quer\u00e9taro, Mexico"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Facultad de Inform\u00e1tica, Universidad Autonoma de Quer\u00e9taro, Av. de las Ciencias S/N, Campus Juriquilla, C.P. 76230, Quer\u00e9taro, Mexico","institution_ids":["https://openalex.org/I157492648"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5087976655","display_name":"Teresa Garcia-Ram\u00edrez","orcid":"https://orcid.org/0000-0002-5524-2002","observed_orcids":["https://orcid.org/0000-0002-5524-2002"]},"institutions":[{"id":"https://openalex.org/I157492648","display_name":"Autonomous University of Queretaro","ror":"https://ror.org/00v8fdc16","country_code":"MX","type":"education","lineage":["https://openalex.org/I157492648"]}],"countries":["MX"],"is_corresponding":false,"raw_author_name":"Teresa Garc\u00eda-Ramirez","raw_affiliation_strings":["Facultad de Inform\u00e1tica, Universidad Autonoma de Quer\u00e9taro, Av. de las Ciencias S/N, Campus Juriquilla, C.P. 76230, Quer\u00e9taro, Mexico"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Facultad de Inform\u00e1tica, Universidad Autonoma de Quer\u00e9taro, Av. de las Ciencias S/N, Campus Juriquilla, C.P. 76230, Quer\u00e9taro, Mexico","institution_ids":["https://openalex.org/I157492648"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5068400798"],"corresponding_institution_ids":["https://openalex.org/I157492648"],"apc_list":{"value":970,"currency":"USD","value_usd":970},"apc_paid":{"value":970,"currency":"USD","value_usd":970},"fwci":null,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"29","issue":null,"first_page":"101985","last_page":"101985"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9994999766349792,"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":0.9994999766349792,"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":9.999999747378752e-05,"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/T12031","display_name":"Speech and dialogue systems","score":0.0,"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/mixtec-language","display_name":"Mixtec language","score":0.9890000224113464},{"id":"https://openalex.org/keywords/low-resource-languages","display_name":"low-resource languages","score":0.6579999923706055},{"id":"https://openalex.org/keywords/word-tokenization","display_name":"word tokenization","score":0.6830000281333923},{"id":"https://openalex.org/keywords/multiword-expressions","display_name":"multiword expressions","score":0.6470000147819519},{"id":"https://openalex.org/keywords/conditional-random-fields","display_name":"conditional random fields","score":0.7429999709129333},{"id":"https://openalex.org/keywords/bert","display_name":"BERT","score":0.890999972820282},{"id":"https://openalex.org/keywords/gpt-4o","display_name":"GPT-4o","score":0.8550000190734863},{"id":"https://openalex.org/keywords/few-shot-prompting","display_name":"few-shot prompting","score":0.9279999732971191},{"id":"https://openalex.org/keywords/semi-automatic-annotation","display_name":"semi-automatic annotation","score":0.7129999995231628}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7878895998001099},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6760023236274719},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5367881655693054},{"id":"https://openalex.org/C2985367798","wikidata":"https://www.wikidata.org/wiki/Q1346592","display_name":"Parallel corpora","level":3,"score":0.4619048237800598},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.34205347299575806},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.11145618557929993},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1016/j.softx.2024.101985","doi":"https://doi.org/10.1016/j.softx.2024.101985","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.softx.2024.101985","pdf_url":null,"source":{"id":"https://openalex.org/S2506067282","display_name":"SoftwareX","issn_l":"2352-7110","issn":["2352-7110"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["cwts-core","doaj","dongbi-d","jufo-1","ki-jl-1","norway-1","poland-200","vabb-shw"],"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"SoftwareX","raw_type":"journal-article"},{"id":"doi:10.2139/ssrn.4918391","doi":"https://doi.org/10.2139/ssrn.4918391","is_oa":true,"landing_page_url":"http://dx.doi.org/10.2139/ssrn.4918391","pdf_url":null,"source":{"id":"https://openalex.org/S4210172589","display_name":"SSRN Electronic Journal","issn_l":"1556-5068","issn":["1556-5068"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I1318003438","host_organization_name":"RELX Group (Netherlands)","host_organization_lineage":["https://openalex.org/I1318003438"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"posted-content"},{"id":"pmh:oai:doaj.org/article:ad57cdcd71f6401cb6b5279570828b62","doi":null,"is_oa":true,"landing_page_url":"https://doaj.org/article/ad57cdcd71f6401cb6b5279570828b62","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"SoftwareX, Vol 29, Iss , Pp 101985- (2025)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1016/j.softx.2024.101985","doi":"https://doi.org/10.1016/j.softx.2024.101985","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.softx.2024.101985","pdf_url":null,"source":{"id":"https://openalex.org/S2506067282","display_name":"SoftwareX","issn_l":"2352-7110","issn":["2352-7110"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["cwts-core","doaj","dongbi-d","jufo-1","ki-jl-1","norway-1","poland-200","vabb-shw"],"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"SoftwareX","raw_type":"journal-article"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G4754294473","display_name":null,"funder_award_id":"20241134","funder_id":"https://openalex.org/F4320324201","funder_display_name":"Secretar\u00eda de Investigaci\u00f3n y Posgrado, Instituto Polit\u00e9cnico Nacional"}],"funders":[{"id":"https://openalex.org/F4320310924","display_name":"Universidad Aut\u00f3noma de Quer\u00e9taro","ror":"https://ror.org/00v8fdc16"},{"id":"https://openalex.org/F4320321694","display_name":"Instituto Polit\u00e9cnico Nacional","ror":"https://ror.org/059sp8j34"},{"id":"https://openalex.org/F4320321739","display_name":"Consejo Nacional de Ciencia y Tecnolog\u00eda","ror":"https://ror.org/059ex5q34"},{"id":"https://openalex.org/F4320324201","display_name":"Secretar\u00eda de Investigaci\u00f3n y Posgrado, Instituto Polit\u00e9cnico Nacional","ror":"https://ror.org/059sp8j34"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W66137051","https://openalex.org/W2003458432","https://openalex.org/W2583877189","https://openalex.org/W2740887992","https://openalex.org/W2805736358","https://openalex.org/W2896457183","https://openalex.org/W2936180161","https://openalex.org/W2965373594","https://openalex.org/W2978017171","https://openalex.org/W2983040767","https://openalex.org/W3031241327","https://openalex.org/W3089204009","https://openalex.org/W3129647673","https://openalex.org/W3161447971","https://openalex.org/W3164626265","https://openalex.org/W3177044084","https://openalex.org/W4200363935","https://openalex.org/W4285137176","https://openalex.org/W4285263196","https://openalex.org/W4292641180","https://openalex.org/W4313215597","https://openalex.org/W4384575584","https://openalex.org/W4385570523","https://openalex.org/W4388562892","https://openalex.org/W4399450154"],"related_works":["https://openalex.org/W3204019825","https://openalex.org/W2143927888","https://openalex.org/W2242707303","https://openalex.org/W2757753881","https://openalex.org/W2123678043","https://openalex.org/W2125885330","https://openalex.org/W2902262852","https://openalex.org/W37319627","https://openalex.org/W1572297637","https://openalex.org/W2251265917"],"abstract_inverted_index":{"In":[0],"this":[1],"work,":[2],"we":[3,37,100],"developed":[4],"the":[5,39,42,54,79],"first":[6],"intelligent":[7],"automatic":[8,149],"grammatical":[9,150],"tagger":[10,20],"for":[11,86,127,148],"a":[12,29,84,102,110,128,153,158],"Spanish\u2013Mixtec":[13,30],"parallel":[14,31],"corpus":[15,32,40],"in":[16],"Mexico.":[17],"The":[18],"proposed":[19,101],"consists":[21],"of":[22,33,130,155,160],"multiple":[23,146],"phases.":[24],"We":[25,82,122,144],"started":[26],"by":[27,57],"collecting":[28],"12,300":[34],"sentences.":[35],"Then,":[36],"tokenized":[38],"at":[41],"word":[43,59,69],"level,":[44],"removing":[45],"empty":[46,51],"lines,":[47],"duplicate":[48],"sentences,":[49],"and":[50,64,67,74,97,109,119,133,157],"terms":[52],"from":[53],"texts,":[55],"followed":[56],"identifying":[58],"units,":[60],"such":[61],"as":[62],"multiword":[63],"compound":[65],"words,":[66],"defined":[68],"classes,":[70],"specifying":[71],"mandatory,":[72],"recommended,":[73],"optional":[75],"characteristics":[76],"according":[77],"to":[78],"EAGLES":[80],"group.":[81],"established":[83],"standard":[85],"annotating":[87],"words":[88,132],"based":[89],"on":[90],"EAGLES,":[91],"considering":[92],"three":[93],"elements:":[94],"attribute,":[95],"value,":[96],"code.":[98],"Finally,":[99],"synthetic":[103],"Mixtec":[104],"tag":[105,112],"using":[106,113,139],"GPT-4,":[107],"GPT-4o,":[108],"manual":[111],"alignment,":[114],"conditional":[115],"random":[116],"fields":[117],"(CRF)":[118],"BERT":[120],"models.":[121],"manually":[123],"annotated":[124,135],"600":[125],"sentences":[126,138],"total":[129],"2800":[131],"semi-automatically":[134],"3000":[136],"more":[137],"GPT-4o":[140],"with":[141],"few-shot":[142],"prompting.":[143],"trained":[145],"models":[147],"tagging,":[151],"achieving":[152],"precision":[154],"0.74":[156],"recall":[159],"0.80.":[161]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-10-16T09:59:22.235173","created_date":"2025-10-10T00:00:00"}
