{"id":"https://openalex.org/W4406940802","doi":"https://doi.org/10.1007/978-3-031-79029-4_13","title":"Aroeira: A Curated Corpus for the Portuguese Language with a Large Number of Tokens","display_name":"Aroeira: A Curated Corpus for the Portuguese Language with a Large Number of Tokens","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4406940802","doi":"https://doi.org/10.1007/978-3-031-79029-4_13"},"language":"en","primary_location":{"id":"doi:10.1007/978-3-031-79029-4_13","doi":"https://doi.org/10.1007/978-3-031-79029-4_13","is_oa":true,"landing_page_url":"https://doi.org/10.1007/978-3-031-79029-4_13","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","jufo-1","ki-jl-1","norway-1","vabb-shw"],"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},"volume":{"id":"https://openalex.org/W4406940879","display_name":"Intelligent Systems"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1007/978-3-031-79029-4_13","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5116073224","display_name":"Thiago Lira","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Thiago Lira","raw_affiliation_strings":["Instituto de Ci\u00eancia e Tecnologia Ita\u00fa-Unibanco (ICTi), S\u00e3o Paulo, Brazil"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Instituto de Ci\u00eancia e Tecnologia Ita\u00fa-Unibanco (ICTi), S\u00e3o Paulo, Brazil","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020902458","display_name":"Fl\u00e1vio Nakasato Ca\u00e7\u00e3o","orcid":"https://orcid.org/0000-0003-4771-6009","observed_orcids":["https://orcid.org/0000-0003-4771-6009"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fl\u00e1vio Ca\u00e7\u00e3o","raw_affiliation_strings":["Instituto de Ci\u00eancia e Tecnologia Ita\u00fa-Unibanco (ICTi), S\u00e3o Paulo, Brazil"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Instituto de Ci\u00eancia e Tecnologia Ita\u00fa-Unibanco (ICTi), S\u00e3o Paulo, Brazil","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006082565","display_name":"Cristiano Antonio de Souza","orcid":"https://orcid.org/0000-0002-9453-3240","observed_orcids":["https://orcid.org/0000-0002-9453-3240"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cinthia Souza","raw_affiliation_strings":["Instituto de Ci\u00eancia e Tecnologia Ita\u00fa-Unibanco (ICTi), S\u00e3o Paulo, Brazil"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Instituto de Ci\u00eancia e Tecnologia Ita\u00fa-Unibanco (ICTi), S\u00e3o Paulo, Brazil","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025194914","display_name":"Jo\u00e3o Pedro Hannauer Valentini","orcid":"https://orcid.org/0000-0002-4168-7609","observed_orcids":["https://orcid.org/0000-0002-4168-7609"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jo\u00e3o Valentini","raw_affiliation_strings":["Instituto de Ci\u00eancia e Tecnologia Ita\u00fa-Unibanco (ICTi), S\u00e3o Paulo, Brazil"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Instituto de Ci\u00eancia e Tecnologia Ita\u00fa-Unibanco (ICTi), S\u00e3o Paulo, Brazil","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085487887","display_name":"Edson Bollis","orcid":"https://orcid.org/0000-0002-0993-784X","observed_orcids":["https://orcid.org/0000-0002-0993-784X"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Edson Bollis","raw_affiliation_strings":["Instituto de Ci\u00eancia e Tecnologia Ita\u00fa-Unibanco (ICTi), S\u00e3o Paulo, Brazil"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Instituto de Ci\u00eancia e Tecnologia Ita\u00fa-Unibanco (ICTi), S\u00e3o Paulo, Brazil","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"Otavio Oliveira","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Otavio Oliveira","raw_affiliation_strings":["Instituto de Ci\u00eancia e Tecnologia Ita\u00fa-Unibanco (ICTi), S\u00e3o Paulo, Brazil"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Instituto de Ci\u00eancia e Tecnologia Ita\u00fa-Unibanco (ICTi), S\u00e3o Paulo, Brazil","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"Renato Almeida","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Renato Almeida","raw_affiliation_strings":["Instituto de Ci\u00eancia e Tecnologia Ita\u00fa-Unibanco (ICTi), S\u00e3o Paulo, Brazil"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Instituto de Ci\u00eancia e Tecnologia Ita\u00fa-Unibanco (ICTi), S\u00e3o Paulo, Brazil","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011465139","display_name":"Maria Lu\u00edsa Delfino Magalh\u00e3es","orcid":"https://orcid.org/0000-0002-8465-4428","observed_orcids":["https://orcid.org/0000-0002-8465-4428"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Marcio Magalh\u00e3es","raw_affiliation_strings":["Instituto de Ci\u00eancia e Tecnologia Ita\u00fa-Unibanco (ICTi), S\u00e3o Paulo, Brazil"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Instituto de Ci\u00eancia e Tecnologia Ita\u00fa-Unibanco (ICTi), S\u00e3o Paulo, Brazil","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053888326","display_name":"Katia Maria Poloni","orcid":"https://orcid.org/0000-0003-1173-2277","observed_orcids":["https://orcid.org/0000-0003-1173-2277"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Katia Poloni","raw_affiliation_strings":["Instituto de Ci\u00eancia e Tecnologia Ita\u00fa-Unibanco (ICTi), S\u00e3o Paulo, Brazil"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Instituto de Ci\u00eancia e Tecnologia Ita\u00fa-Unibanco (ICTi), S\u00e3o Paulo, Brazil","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100741664","display_name":"Andr\u00e9 Oliveira","orcid":"https://orcid.org/0000-0002-9545-3736","observed_orcids":["https://orcid.org/0000-0002-9545-3736"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Andre Oliveira","raw_affiliation_strings":["Instituto de Ci\u00eancia e Tecnologia Ita\u00fa-Unibanco (ICTi), S\u00e3o Paulo, Brazil"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Instituto de Ci\u00eancia e Tecnologia Ita\u00fa-Unibanco (ICTi), S\u00e3o Paulo, Brazil","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038120583","display_name":"Lucas Francisco Amaral Orosco Pellicer","orcid":"https://orcid.org/0000-0003-2827-7602","observed_orcids":["https://orcid.org/0000-0003-2827-7602"]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Lucas Pellicer","raw_affiliation_strings":["Instituto de Ci\u00eancia e Tecnologia Ita\u00fa-Unibanco (ICTi), S\u00e3o Paulo, Brazil"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Instituto de Ci\u00eancia e Tecnologia Ita\u00fa-Unibanco (ICTi), S\u00e3o Paulo, Brazil","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5038120583"],"corresponding_institution_ids":[],"apc_list":{"value":5000,"currency":"EUR","value_usd":5392},"apc_paid":{"value":5000,"currency":"EUR","value_usd":5392},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.00823102,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"185","last_page":"199"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.7728999853134155,"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":0.7728999853134155,"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":0.22030000388622284,"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/T10664","display_name":"Sentiment Analysis and Opinion Mining","score":0.0013000000035390258,"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/brazilian-portuguese","display_name":"Brazilian Portuguese","score":0.7929999828338623},{"id":"https://openalex.org/keywords/large-language-model-training-data","display_name":"large language model training data","score":0.6980000138282776},{"id":"https://openalex.org/keywords/low-resource-languages","display_name":"low-resource languages","score":0.7179999947547913},{"id":"https://openalex.org/keywords/corpus-curation","display_name":"corpus curation","score":0.6660000085830688},{"id":"https://openalex.org/keywords/language-identification","display_name":"language identification","score":0.7490000128746033}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8721928000450134},{"id":"https://openalex.org/C35219183","wikidata":"https://www.wikidata.org/wiki/Q5146","display_name":"Portuguese","level":2,"score":0.6733257174491882},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5620659589767456},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4294775128364563},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.21476876735687256},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/978-3-031-79029-4_13","doi":"https://doi.org/10.1007/978-3-031-79029-4_13","is_oa":true,"landing_page_url":"https://doi.org/10.1007/978-3-031-79029-4_13","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","jufo-1","ki-jl-1","norway-1","vabb-shw"],"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"}],"best_oa_location":{"id":"doi:10.1007/978-3-031-79029-4_13","doi":"https://doi.org/10.1007/978-3-031-79029-4_13","is_oa":true,"landing_page_url":"https://doi.org/10.1007/978-3-031-79029-4_13","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","jufo-1","ki-jl-1","norway-1","vabb-shw"],"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W2117373735","https://openalex.org/W2468328197","https://openalex.org/W2806758205","https://openalex.org/W2981852735","https://openalex.org/W3019416653","https://openalex.org/W3030163527","https://openalex.org/W3032388710","https://openalex.org/W3089430725","https://openalex.org/W3096266342","https://openalex.org/W3169113923","https://openalex.org/W3177057043","https://openalex.org/W3183430109","https://openalex.org/W4225156065","https://openalex.org/W4284691825","https://openalex.org/W4380319657","https://openalex.org/W4385571141","https://openalex.org/W4387522367","https://openalex.org/W4399528455","https://openalex.org/W4404783303","https://openalex.org/W4415725257","https://openalex.org/W6601375367"],"related_works":["https://openalex.org/W4415933221","https://openalex.org/W4412987451","https://openalex.org/W6986985037","https://openalex.org/W7160196674","https://openalex.org/W7160149423","https://openalex.org/W7212001254","https://openalex.org/W4392012793","https://openalex.org/W4394708653","https://openalex.org/W6908989655","https://openalex.org/W4312697031"],"abstract_inverted_index":{"The":[0,71,93,115],"emphasis":[1],"on":[2,66],"constructing":[3],"extensive":[4],"datasets":[5,20],"for":[6,21,38,54,111],"training":[7,55],"large":[8,56],"language":[9,57,99],"models":[10,58],"(LLM)":[11],"has":[12],"recently":[13],"increased,":[14],"and":[15,27,104,107,122],"current":[16],"literature":[17],"predominantly":[18],"features":[19],"high-resource":[22],"languages":[23],"such":[24],"as":[25],"English":[26],"Chinese.":[28],"However,":[29],"there":[30],"is":[31],"a":[32,49,64,86],"notable":[33],"scarcity":[34],"of":[35,75,78,102],"high-quality":[36],"corpora":[37],"the":[39,60,67,112,128],"Portuguese":[40,61,69,113],"language.":[41,114],"To":[42],"address":[43],"this":[44,134],"limitation,":[45],"we":[46],"propose":[47],"Aroeira,":[48],"curated":[50],"corpus":[51,117,132],"explicitly":[52],"designed":[53],"in":[59,133],"language,":[62],"with":[63],"focus":[65],"Brazilian":[68],"one.":[70],"Aroeira":[72],"Corpus":[73],"consists":[74],"100":[76],"GB":[77],"texts":[79],"from":[80],"various":[81],"internet":[82],"platforms,":[83],"processed":[84],"through":[85],"comprehensive":[87],"pipeline":[88,94],"to":[89],"ensure":[90],"superior":[91],"quality.":[92],"handles":[95],"downloading,":[96],"text":[97],"extraction,":[98],"identification,":[100],"application":[101],"quality":[103],"bias":[105],"filters,":[106],"storage,":[108],"all":[109],"tailored":[110],"resulting":[116],"contains":[118],"35.3":[119],"million":[120],"documents":[121],"over":[123],"15.1":[124],"billion":[125],"tokens,":[126],"surpassing":[127],"largest":[129],"previously":[130],"available":[131],"domain.":[135]},"counts_by_year":[],"updated_date":"2026-10-16T09:59:22.235173","created_date":"2025-01-30T00:00:00"}
