{"id":"https://openalex.org/W2079597242","doi":"https://doi.org/10.1186/s13173-014-0020-x","title":"Evaluating word embeddings and a revised corpus for part-of-speech tagging in Portuguese","display_name":"Evaluating word embeddings and a revised corpus for part-of-speech tagging in Portuguese","publication_year":2015,"publication_date":"2015-02-05","ids":{"openalex":"https://openalex.org/W2079597242","doi":"https://doi.org/10.1186/s13173-014-0020-x","mag":"2079597242"},"language":"en","primary_location":{"id":"doi:10.1186/s13173-014-0020-x","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13173-014-0020-x","pdf_url":"https://journal-bcs.springeropen.com/counter/pdf/10.1186/s13173-014-0020-x","source":{"id":"https://openalex.org/S69801987","display_name":"Journal of the Brazilian Computer Society","issn_l":"0104-6500","issn":["0104-6500","1678-4804"],"is_oa":true,"is_in_doaj":true,"is_core":true,"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":"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":"Journal of the Brazilian Computer Society","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://journal-bcs.springeropen.com/counter/pdf/10.1186/s13173-014-0020-x","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5036870275","display_name":"Erick Fonseca","orcid":"https://orcid.org/0000-0002-3726-139X"},"institutions":[{"id":"https://openalex.org/I17974374","display_name":"Universidade de S\u00e3o Paulo","ror":"https://ror.org/036rp1748","country_code":"BR","type":"education","lineage":["https://openalex.org/I17974374"]}],"countries":["BR"],"is_corresponding":true,"raw_author_name":"Erick R Fonseca","raw_affiliation_strings":["Institute of Mathematics and Computer Science (ICMC), University of S\u00e3o Paulo, Av. Trabalhador S\u00e3o-Carlense, S\u00e3o Carlos, 400, 13566-590, Brazil","Institute of Mathematics and Computer Science (ICMC), University of S\u00e3o Paulo, Av. Trabalhador S\u00e3o-Carlense, S\u00e3o Carlos, Brazil"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Mathematics and Computer Science (ICMC), University of S\u00e3o Paulo, Av. Trabalhador S\u00e3o-Carlense, S\u00e3o Carlos, 400, 13566-590, Brazil","institution_ids":["https://openalex.org/I17974374"]},{"raw_affiliation_string":"Institute of Mathematics and Computer Science (ICMC), University of S\u00e3o Paulo, Av. Trabalhador S\u00e3o-Carlense, S\u00e3o Carlos, Brazil","institution_ids":["https://openalex.org/I17974374"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047073710","display_name":"Jo\u00e3o Lu\u00eds Garcia Rosa","orcid":"https://orcid.org/0000-0002-9491-9434"},"institutions":[{"id":"https://openalex.org/I17974374","display_name":"Universidade de S\u00e3o Paulo","ror":"https://ror.org/036rp1748","country_code":"BR","type":"education","lineage":["https://openalex.org/I17974374"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Jo\u00e3o Lu\u00eds G Rosa","raw_affiliation_strings":["Institute of Mathematics and Computer Science (ICMC), University of S\u00e3o Paulo, Av. Trabalhador S\u00e3o-Carlense, S\u00e3o Carlos, 400, 13566-590, Brazil","Institute of Mathematics and Computer Science (ICMC), University of S\u00e3o Paulo, Av. Trabalhador S\u00e3o-Carlense, S\u00e3o Carlos, Brazil"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Mathematics and Computer Science (ICMC), University of S\u00e3o Paulo, Av. Trabalhador S\u00e3o-Carlense, S\u00e3o Carlos, 400, 13566-590, Brazil","institution_ids":["https://openalex.org/I17974374"]},{"raw_affiliation_string":"Institute of Mathematics and Computer Science (ICMC), University of S\u00e3o Paulo, Av. Trabalhador S\u00e3o-Carlense, S\u00e3o Carlos, Brazil","institution_ids":["https://openalex.org/I17974374"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5059202822","display_name":"Sandra Maria Alu\u00edsio","orcid":"https://orcid.org/0000-0001-5108-2630"},"institutions":[{"id":"https://openalex.org/I17974374","display_name":"Universidade de S\u00e3o Paulo","ror":"https://ror.org/036rp1748","country_code":"BR","type":"education","lineage":["https://openalex.org/I17974374"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Sandra Maria Alu\u00edsio","raw_affiliation_strings":["Institute of Mathematics and Computer Science (ICMC), University of S\u00e3o Paulo, Av. Trabalhador S\u00e3o-Carlense, S\u00e3o Carlos, 400, 13566-590, Brazil","Institute of Mathematics and Computer Science (ICMC), University of S\u00e3o Paulo, Av. Trabalhador S\u00e3o-Carlense, S\u00e3o Carlos, Brazil"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Mathematics and Computer Science (ICMC), University of S\u00e3o Paulo, Av. Trabalhador S\u00e3o-Carlense, S\u00e3o Carlos, 400, 13566-590, Brazil","institution_ids":["https://openalex.org/I17974374"]},{"raw_affiliation_string":"Institute of Mathematics and Computer Science (ICMC), University of S\u00e3o Paulo, Av. Trabalhador S\u00e3o-Carlense, S\u00e3o Carlos, Brazil","institution_ids":["https://openalex.org/I17974374"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5036870275"],"corresponding_institution_ids":["https://openalex.org/I17974374"],"apc_list":null,"apc_paid":null,"fwci":10.4765,"has_fulltext":true,"cited_by_count":59,"citation_normalized_percentile":{"value":0.98186292,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"21","issue":"1","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":1.0,"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"}},"topics":[{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":1.0,"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"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9991000294685364,"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/T13629","display_name":"Text Readability and Simplification","score":0.9984999895095825,"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/part-of-speech-tagging","display_name":"Part-of-speech tagging","score":0.8475137948989868},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7571007013320923},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.713931679725647},{"id":"https://openalex.org/keywords/portuguese","display_name":"Portuguese","score":0.7128666639328003},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.6590872406959534},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5457748770713806},{"id":"https://openalex.org/keywords/part-of-speech","display_name":"Part of speech","score":0.5112593173980713},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.42646387219429016},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.384225994348526}],"concepts":[{"id":"https://openalex.org/C2780684714","wikidata":"https://www.wikidata.org/wiki/Q1271424","display_name":"Part-of-speech tagging","level":3,"score":0.8475137948989868},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7571007013320923},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.713931679725647},{"id":"https://openalex.org/C35219183","wikidata":"https://www.wikidata.org/wiki/Q5146","display_name":"Portuguese","level":2,"score":0.7128666639328003},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.6590872406959534},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5457748770713806},{"id":"https://openalex.org/C123406163","wikidata":"https://www.wikidata.org/wiki/Q82042","display_name":"Part of speech","level":2,"score":0.5112593173980713},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.42646387219429016},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.384225994348526},{"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:10.1186/s13173-014-0020-x","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13173-014-0020-x","pdf_url":"https://journal-bcs.springeropen.com/counter/pdf/10.1186/s13173-014-0020-x","source":{"id":"https://openalex.org/S69801987","display_name":"Journal of the Brazilian Computer Society","issn_l":"0104-6500","issn":["0104-6500","1678-4804"],"is_oa":true,"is_in_doaj":true,"is_core":true,"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":"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":"Journal of the Brazilian Computer Society","raw_type":"journal-article"},{"id":"pmh:oai:www.producao.usp.br:BDPI/50949","is_oa":false,"landing_page_url":"http://www.producao.usp.br/handle/BDPI/50949","pdf_url":null,"source":{"id":"https://openalex.org/S4306402433","display_name":"Portuguese National Funding Agency for Science, Research and Technology (RCAAP Project by FCT)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"reponame:Reposit\u00f3rio Institucional da USP","raw_type":"publishedVersion"},{"id":"pmh:002678220","is_oa":true,"landing_page_url":"http://dx.doi.org/10.1186/s13173-014-0020-x","pdf_url":null,"source":{"id":"https://openalex.org/S4306402641","display_name":"LA Referencia (Red Federada de Repositorios Institucionales de Publicaciones Cient\u00edficas)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4383465926","host_organization_name":"LA Referencia","host_organization_lineage":["https://openalex.org/I4383465926"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"reponame:Reposit\u00f3rio Institucional da USP (Biblioteca Digital da Produ\u00e7\u00e3o Intelectual)","raw_type":"info:eu-repo/semantics/publishedVersion"}],"best_oa_location":{"id":"doi:10.1186/s13173-014-0020-x","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13173-014-0020-x","pdf_url":"https://journal-bcs.springeropen.com/counter/pdf/10.1186/s13173-014-0020-x","source":{"id":"https://openalex.org/S69801987","display_name":"Journal of the Brazilian Computer Society","issn_l":"0104-6500","issn":["0104-6500","1678-4804"],"is_oa":true,"is_in_doaj":true,"is_core":true,"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":"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":"Journal of the Brazilian Computer Society","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.7300000190734863}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2079597242.pdf","grobid_xml":"https://content.openalex.org/works/W2079597242.grobid-xml"},"referenced_works_count":33,"referenced_works":["https://openalex.org/W60497934","https://openalex.org/W80549136","https://openalex.org/W98255950","https://openalex.org/W168564468","https://openalex.org/W1481637566","https://openalex.org/W1662133657","https://openalex.org/W1874835824","https://openalex.org/W1889268436","https://openalex.org/W1975311598","https://openalex.org/W1981617416","https://openalex.org/W1991133427","https://openalex.org/W2092594518","https://openalex.org/W2101609803","https://openalex.org/W2107611725","https://openalex.org/W2117130368","https://openalex.org/W2117995488","https://openalex.org/W2124776405","https://openalex.org/W2158139315","https://openalex.org/W2158899491","https://openalex.org/W2251012068","https://openalex.org/W2251939518","https://openalex.org/W2324765952","https://openalex.org/W2489487449","https://openalex.org/W2500477757","https://openalex.org/W2506082631","https://openalex.org/W2529806503","https://openalex.org/W2592076957","https://openalex.org/W2594306580","https://openalex.org/W2733628661","https://openalex.org/W2912179220","https://openalex.org/W2913074406","https://openalex.org/W2950577311","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W1965453504","https://openalex.org/W2396342956","https://openalex.org/W3128305375","https://openalex.org/W2626026432","https://openalex.org/W2251183413","https://openalex.org/W2949108231","https://openalex.org/W2486838646","https://openalex.org/W2006539681","https://openalex.org/W2046224275","https://openalex.org/W2790645792"],"abstract_inverted_index":{"Part-of-speech":[0],"tagging":[1],"is":[2,23],"an":[3,35],"important":[4],"preprocessing":[5],"step":[6],"in":[7,19,29,50,56,66,109,126],"many":[8],"natural":[9],"language":[10],"processing":[11],"applications.":[12],"Despite":[13],"much":[14],"work":[15,129],"already":[16],"carried":[17],"out":[18],"this":[20],"field,":[21],"there":[22],"still":[24],"room":[25],"for":[26,118,147],"improvement,":[27],"especially":[28],"Portuguese.":[30],"We":[31,52,81,97,113],"experiment":[32],"here":[33,131],"with":[34,102,133],"architecture":[36],"based":[37],"on":[38],"neural":[39],"networks":[40],"and":[41,44,72,75,92,105,122,141],"word":[42,90,120],"embeddings,":[43],"that":[45],"has":[46],"achieved":[47],"promising":[48],"results":[49,108],"English.":[51],"tested":[53],"our":[54,99],"classifier":[55],"different":[57,87,116],"corpora:":[58],"a":[59,134,142],"new":[60,111,135,144],"revision":[61,136],"of":[62,79,85,89,137],"the":[63,83,110,138],"Mac-Morpho":[64,139],"corpus,":[65],"which":[67],"we":[68],"merged":[69],"some":[70],"tags":[71],"performed":[73],"corrections":[74],"two":[76],"previous":[77],"versions":[78],"it.":[80],"evaluate":[82],"impact":[84],"using":[86],"types":[88],"embeddings":[91,121],"explicit":[93],"features":[94,124],"as":[95],"input.":[96],"compare":[98],"tagger\u2019s":[100],"performance":[101],"other":[103],"systems":[104],"achieve":[106],"state-of-the-art":[107,143],"corpus.":[112],"show":[114],"how":[115],"methods":[117],"generating":[119],"additional":[123],"differ":[125],"accuracy.":[127],"The":[128],"reported":[130],"contributes":[132],"corpus":[140],"tagger":[145],"available":[146],"use":[148],"out-of-the-box.":[149]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2023,"cited_by_count":9},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":8},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":6},{"year":2018,"cited_by_count":9},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":11},{"year":2015,"cited_by_count":1}],"updated_date":"2026-07-02T09:51:11.867554","created_date":"2016-06-24T00:00:00"}
