{"id":"https://openalex.org/W3081487141","doi":"https://doi.org/10.31513/linguistica.2020.v16n1a31709","title":"Sobre a constitui\u00e7\u00e3o de corpora para l\u00ednguas com poucos recursos","display_name":"Sobre a constitui\u00e7\u00e3o de corpora para l\u00ednguas com poucos recursos","publication_year":2020,"publication_date":"2020-04-30","ids":{"openalex":"https://openalex.org/W3081487141","doi":"https://doi.org/10.31513/linguistica.2020.v16n1a31709","mag":"3081487141"},"language":"pt","primary_location":{"id":"doi:10.31513/linguistica.2020.v16n1a31709","doi":"https://doi.org/10.31513/linguistica.2020.v16n1a31709","is_oa":true,"landing_page_url":"https://doi.org/10.31513/linguistica.2020.v16n1a31709","pdf_url":null,"source":{"id":"https://openalex.org/S4210205747","display_name":"Revista Lingu\u00ed\u0283tica","issn_l":"1808-835X","issn":["1808-835X","2238-975X"],"is_oa":true,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","erih-plus"],"host_organization":"https://openalex.org/P4310312367","host_organization_name":"Federal University of Rio de Janeiro","host_organization_lineage":["https://openalex.org/P4310312367"],"host_organization_lineage_names":["Federal University of Rio de Janeiro"],"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":"Revista Lingu\u00ed\u0283tica","raw_type":"journal-article"},"volume":null,"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://doi.org/10.31513/linguistica.2020.v16n1a31709","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5090520403","display_name":"L\u00edlian Teixeira de Sousa","orcid":"https://orcid.org/0000-0001-9911-2587","observed_orcids":["https://orcid.org/0000-0001-9911-2587"]},"institutions":[{"id":"https://openalex.org/I126158947","display_name":"Universidade Federal da Bahia","ror":"https://ror.org/03k3p7647","country_code":"BR","type":"education","lineage":["https://openalex.org/I126158947"]}],"countries":["BR"],"is_corresponding":true,"raw_author_name":"L\u00edlian Teixeira de Sousa","raw_affiliation_strings":["Universidade Federal da Bahia (UFBa)"],"raw_orcid":"https://orcid.org/0000-0001-9911-2587","affiliations":[{"raw_affiliation_string":"Universidade Federal da Bahia (UFBa)","institution_ids":["https://openalex.org/I126158947"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5090520403"],"corresponding_institution_ids":["https://openalex.org/I126158947"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.10190554,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"16","issue":"1","first_page":"43","last_page":"61"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13623","display_name":"Linguistic Studies and Language Acquisition","score":0.33399999141693115,"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/T13623","display_name":"Linguistic Studies and Language Acquisition","score":0.33399999141693115,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.27320000529289246,"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/T12353","display_name":"Lexicography and Language Studies","score":0.09189999848604202,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/corpus-construction","display_name":"corpus construction","score":0.878000020980835},{"id":"https://openalex.org/keywords/low-resource-languages","display_name":"low-resource languages","score":0.9419999718666077},{"id":"https://openalex.org/keywords/endangered-languages","display_name":"endangered languages","score":0.7229999899864197},{"id":"https://openalex.org/keywords/corpus-linguistics","display_name":"corpus linguistics","score":0.7789999842643738},{"id":"https://openalex.org/keywords/language-documentation","display_name":"language documentation","score":0.6499999761581421},{"id":"https://openalex.org/keywords/language-revitalization","display_name":"language revitalization","score":0.4189999997615814}],"concepts":[{"id":"https://openalex.org/C15708023","wikidata":"https://www.wikidata.org/wiki/Q80083","display_name":"Humanities","level":1,"score":0.5738152861595154},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.45901644229888916},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.3632497489452362}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.31513/linguistica.2020.v16n1a31709","doi":"https://doi.org/10.31513/linguistica.2020.v16n1a31709","is_oa":true,"landing_page_url":"https://doi.org/10.31513/linguistica.2020.v16n1a31709","pdf_url":null,"source":{"id":"https://openalex.org/S4210205747","display_name":"Revista Lingu\u00ed\u0283tica","issn_l":"1808-835X","issn":["1808-835X","2238-975X"],"is_oa":true,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","erih-plus"],"host_organization":"https://openalex.org/P4310312367","host_organization_name":"Federal University of Rio de Janeiro","host_organization_lineage":["https://openalex.org/P4310312367"],"host_organization_lineage_names":["Federal University of Rio de Janeiro"],"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":"Revista Lingu\u00ed\u0283tica","raw_type":"journal-article"},{"id":"pmh:oai:revistas.ufrj.br:article/31709","doi":null,"is_oa":true,"landing_page_url":"https://revistas.ufrj.br/index.php/rl/article/view/31709","pdf_url":"https://revistas.ufrj.br/index.php/rl/article/download/31709/20597","source":{"id":"https://openalex.org/S4210205747","display_name":"Revista Lingu\u00ed\u0283tica","issn_l":"1808-835X","issn":["1808-835X","2238-975X"],"is_oa":true,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","erih-plus"],"host_organization":"https://openalex.org/P4310312367","host_organization_name":"Federal University of Rio de Janeiro","host_organization_lineage":["https://openalex.org/P4310312367"],"host_organization_lineage_names":["Federal University of Rio de Janeiro"],"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":"1808-835X","raw_type":"info:eu-repo/semantics/article"},{"id":"pmh:oai:doaj.org/article:c252baf0870d45dca0bcf5235c6081a8","doi":null,"is_oa":true,"landing_page_url":"https://doaj.org/article/c252baf0870d45dca0bcf5235c6081a8","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":"Revista Lingu\u00edstica, Vol 16, Iss 1, Pp 43-61 (2020)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.31513/linguistica.2020.v16n1a31709","doi":"https://doi.org/10.31513/linguistica.2020.v16n1a31709","is_oa":true,"landing_page_url":"https://doi.org/10.31513/linguistica.2020.v16n1a31709","pdf_url":null,"source":{"id":"https://openalex.org/S4210205747","display_name":"Revista Lingu\u00ed\u0283tica","issn_l":"1808-835X","issn":["1808-835X","2238-975X"],"is_oa":true,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","erih-plus"],"host_organization":"https://openalex.org/P4310312367","host_organization_name":"Federal University of Rio de Janeiro","host_organization_lineage":["https://openalex.org/P4310312367"],"host_organization_lineage_names":["Federal University of Rio de Janeiro"],"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":"Revista Lingu\u00ed\u0283tica","raw_type":"journal-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W52772492","https://openalex.org/W937271966","https://openalex.org/W1030963941","https://openalex.org/W1988917863","https://openalex.org/W2020644894","https://openalex.org/W2041359823","https://openalex.org/W2101844505","https://openalex.org/W2156972453","https://openalex.org/W2625499837","https://openalex.org/W2806467027","https://openalex.org/W4210870583"],"related_works":["https://openalex.org/W1942174566","https://openalex.org/W3206135413","https://openalex.org/W4366164114","https://openalex.org/W2180330045","https://openalex.org/W7133341561","https://openalex.org/W2288509019","https://openalex.org/W2239103828","https://openalex.org/W2291290636","https://openalex.org/W4206963759","https://openalex.org/W1565852031"],"abstract_inverted_index":{"O":[0],"uso":[1],"de":[2,15,34,51,65,80,108,110,133,138,150,167,173,183,190,207,218,226],"corpora":[3,91,125,137,149,191],"em":[4],"estudos":[5],"lingu\u00edsticos":[6],"\u00e9":[7,17],"bastante":[8,100],"antigo,":[9],"j\u00e1":[10],"a":[11,28,41,73,78,106,156,188,234],"\u00e1rea":[12,42],"da":[13,131],"Lingu\u00edstica":[14,132,206],"Corpus":[16],"relativamente":[18],"nova,":[19],"tendo":[20],"sua":[21],"origem":[22],"vinculada":[23],"\u00e0":[24],"amplia\u00e7\u00e3o":[25],"do":[26],"acesso":[27],"computadores":[29],"e,":[30,160],"consequentemente,":[31],"ao":[32],"Processamento":[33],"Linguagem":[35],"Natural":[36],"(PLN).":[37],"\u00c0":[38],"medida":[39],"que":[40,147,187,198],"foi":[43,53],"ganhando":[44],"influ\u00eancia":[45],"na":[46,82,236],"pesquisa":[47],"lingu\u00edstica,":[48],"o":[49,115],"conceito":[50],"corpus":[52,169],"se":[54,74],"tornando":[55],"mais":[56,158],"espec\u00edfico":[57],"e":[58,62,69,93,135,171,212],"elementos":[59],"como":[60],"amplitude":[61],"refer\u00eancia,":[63],"al\u00e9m":[64],"legibilidade":[66],"por":[67,103,119,180],"m\u00e1quina":[68],"tamanho":[70],"finito,":[71],"passaram":[72],"tornar":[75],"fundamentais":[76],"para":[77,105,192,229],"composi\u00e7\u00e3o":[79],"amostras":[81],"\u00e1rea.":[83],"Ao":[84],"mesmo":[85],"tempo,":[86],"no":[87],"entanto,":[88],"foram":[89],"surgindo":[90],"menores":[92],"bem":[94],"menos":[95],"amplos":[96],"constitu\u00eddos":[97],"com":[98,140,152,194],"objetivos":[99],"distintos,":[101],"como,":[102],"exemplo,":[104],"realiza\u00e7\u00e3o":[107],"documenta\u00e7\u00e3o":[109],"l\u00ednguas":[111,139,151,193],"amea\u00e7adas.":[112],"Partindo":[113],"disso,":[114],"presente":[116],"artigo":[117],"tem":[118],"objetivo":[120],"discutir":[121],"as":[122],"diferen\u00e7as":[123],"entre":[124],"\u201cprotot\u00edpicos\u201d":[126],"criados":[127],"segundo":[128],"os":[129,136,148,164,202,213],"pressupostos":[130],"Corpus,":[134,208],"pouca":[141],"presen\u00e7a":[142],"digital":[143],"(less-resourced":[144],"languages).":[145],"Mostro":[146],"pouco":[153],"recursos":[154],"tendem":[155],"ser":[157,210,216],"especializados":[159],"dificilmente,":[161],"cumprem":[162],"todos":[163,201],"crit\u00e9rios":[165,203],"exigidos":[166],"um":[168],"amplo":[170],"representativo":[172],"uma":[174],"l\u00edngua.":[175],"Apesar":[176],"dos":[177],"limites":[178],"impostos":[179],"quest\u00f5es":[181],"espec\u00edficas":[182],"cada":[184],"l\u00edngua,":[185],"concluo":[186],"constitui\u00e7\u00e3o":[189],"poucos":[195],"recursos,":[196],"ainda":[197],"n\u00e3o":[199],"cumpram":[200],"propostos":[204],"pela":[205],"devem":[209,215],"realizados,":[211],"resultados":[214],"aproveitados":[217],"diversas":[219],"formas,":[220],"seja":[221],"gerando":[222],"novas":[223],"tecnologias,":[224],"servindo":[225],"suporte":[227],"emp\u00edrico":[228],"teorias":[230],"lingu\u00edsticas":[231],"ou":[232],"promovendo":[233],"l\u00edngua":[235],"comunidade.":[237]},"counts_by_year":[],"updated_date":"2026-10-16T09:59:22.235173","created_date":"2020-09-01T00:00:00"}
