{"id":"https://openalex.org/W4225752875","doi":"https://doi.org/10.3390/bdcc6010008","title":"An Empirical Comparison of Portuguese and Multilingual BERT Models for Auto-Classification of NCM Codes in International Trade","display_name":"An Empirical Comparison of Portuguese and Multilingual BERT Models for Auto-Classification of NCM Codes in International Trade","publication_year":2022,"publication_date":"2022-01-10","ids":{"openalex":"https://openalex.org/W4225752875","doi":"https://doi.org/10.3390/bdcc6010008"},"language":"en","primary_location":{"id":"doi:10.3390/bdcc6010008","is_oa":true,"landing_page_url":"https://doi.org/10.3390/bdcc6010008","pdf_url":"https://www.mdpi.com/2504-2289/6/1/8/pdf?version=1641806745","source":{"id":"https://openalex.org/S4210238752","display_name":"Big Data and Cognitive Computing","issn_l":"2504-2289","issn":["2504-2289"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Big Data and Cognitive Computing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.mdpi.com/2504-2289/6/1/8/pdf?version=1641806745","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5032998033","display_name":"Roberta Rodrigues de Lima","orcid":"https://orcid.org/0009-0001-9490-1509"},"institutions":[{"id":"https://openalex.org/I4210144729","display_name":"Universidade do Vale do Itaja\u00ed","ror":"https://ror.org/041pjwa23","country_code":"BR","type":"education","lineage":["https://openalex.org/I4210144729"]}],"countries":["BR"],"is_corresponding":true,"raw_author_name":"Roberta Rodrigues de Lima","raw_affiliation_strings":["Laboratory of Applied Intelligence, School of the Sea Science and Technology-University of Vale do Itaja\u00ed, Itaja\u00ed 88302-901, Brazil"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Laboratory of Applied Intelligence, School of the Sea Science and Technology-University of Vale do Itaja\u00ed, Itaja\u00ed 88302-901, Brazil","institution_ids":["https://openalex.org/I4210144729"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016608746","display_name":"Anita Maria da Rocha Fernandes","orcid":"https://orcid.org/0000-0002-2986-5353"},"institutions":[{"id":"https://openalex.org/I4210144729","display_name":"Universidade do Vale do Itaja\u00ed","ror":"https://ror.org/041pjwa23","country_code":"BR","type":"education","lineage":["https://openalex.org/I4210144729"]}],"countries":["BR"],"is_corresponding":true,"raw_author_name":"Anita M. R. Fernandes","raw_affiliation_strings":["Laboratory of Applied Intelligence, School of the Sea Science and Technology-University of Vale do Itaja\u00ed, Itaja\u00ed 88302-901, Brazil"],"raw_orcid":"https://orcid.org/0000-0002-2986-5353","affiliations":[{"raw_affiliation_string":"Laboratory of Applied Intelligence, School of the Sea Science and Technology-University of Vale do Itaja\u00ed, Itaja\u00ed 88302-901, Brazil","institution_ids":["https://openalex.org/I4210144729"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087644532","display_name":"James Roberto Bombasar","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"James Roberto Bombasar","raw_affiliation_strings":["Analysis and Systems Development Course, Centro Universit\u00e1rio Avantis, Balne\u00e1rio Cambori\u00fa 88339-125, Brazil"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Analysis and Systems Development Course, Centro Universit\u00e1rio Avantis, Balne\u00e1rio Cambori\u00fa 88339-125, Brazil","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058494643","display_name":"Bruno Alves da Silva","orcid":"https://orcid.org/0000-0002-7995-0695"},"institutions":[{"id":"https://openalex.org/I4210144729","display_name":"Universidade do Vale do Itaja\u00ed","ror":"https://ror.org/041pjwa23","country_code":"BR","type":"education","lineage":["https://openalex.org/I4210144729"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Bruno Alves da Silva","raw_affiliation_strings":["Laboratory of Applied Intelligence, School of the Sea Science and Technology-University of Vale do Itaja\u00ed, Itaja\u00ed 88302-901, Brazil"],"raw_orcid":"https://orcid.org/0000-0002-7995-0695","affiliations":[{"raw_affiliation_string":"Laboratory of Applied Intelligence, School of the Sea Science and Technology-University of Vale do Itaja\u00ed, Itaja\u00ed 88302-901, Brazil","institution_ids":["https://openalex.org/I4210144729"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034688411","display_name":"Paul Crocker","orcid":"https://orcid.org/0000-0001-6824-6136"},"institutions":[{"id":"https://openalex.org/I161321875","display_name":"University of Beira Interior","ror":"https://ror.org/03nf36p02","country_code":"PT","type":"education","lineage":["https://openalex.org/I161321875"]},{"id":"https://openalex.org/I4210120471","display_name":"Instituto de Telecomunica\u00e7\u00f5es","ror":"https://ror.org/02ht4fk33","country_code":"PT","type":"nonprofit","lineage":["https://openalex.org/I4210120471"]}],"countries":["PT"],"is_corresponding":false,"raw_author_name":"Paul Crocker","raw_affiliation_strings":["Instituto de Telecomunica\u00e7\u00f5es and Departamento de Inform\u00e1tica, Universidade da Beira Interior, 6201-001 Covilh\u00e3, Portugal"],"raw_orcid":"https://orcid.org/0000-0001-6824-6136","affiliations":[{"raw_affiliation_string":"Instituto de Telecomunica\u00e7\u00f5es and Departamento de Inform\u00e1tica, Universidade da Beira Interior, 6201-001 Covilh\u00e3, Portugal","institution_ids":["https://openalex.org/I161321875","https://openalex.org/I4210120471"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038022273","display_name":"Valderi Reis Quietinho Leithardt","orcid":"https://orcid.org/0000-0003-0446-9271"},"institutions":[{"id":"https://openalex.org/I4210165014","display_name":"Polytechnic Institute of Portalegre","ror":"https://ror.org/05vnksv67","country_code":"PT","type":"education","lineage":["https://openalex.org/I4210165014"]},{"id":"https://openalex.org/I88596544","display_name":"Universidade Lus\u00f3fona","ror":"https://ror.org/05xxfer42","country_code":"PT","type":"education","lineage":["https://openalex.org/I88596544"]}],"countries":["PT"],"is_corresponding":false,"raw_author_name":"Valderi Reis Quietinho Leithardt","raw_affiliation_strings":["COPELABS, Lus\u00f3fona University of Humanities and Technologies, Campo Grande 376, 1749-024 Lisboa, Portugal","VALORIZA, Research Center for Endogenous Resources Valorization, Instituto Polit\u00e9cnico de Portalegre, 7300-555 Portalegre, Portugal"],"raw_orcid":"https://orcid.org/0000-0003-0446-9271","affiliations":[{"raw_affiliation_string":"COPELABS, Lus\u00f3fona University of Humanities and Technologies, Campo Grande 376, 1749-024 Lisboa, Portugal","institution_ids":["https://openalex.org/I88596544"]},{"raw_affiliation_string":"VALORIZA, Research Center for Endogenous Resources Valorization, Instituto Polit\u00e9cnico de Portalegre, 7300-555 Portalegre, Portugal","institution_ids":["https://openalex.org/I4210165014"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5016608746","https://openalex.org/A5032998033"],"corresponding_institution_ids":["https://openalex.org/I4210144729"],"apc_list":{"value":1400,"currency":"CHF","value_usd":1515},"apc_paid":{"value":1400,"currency":"CHF","value_usd":1515},"fwci":1.3872,"has_fulltext":true,"cited_by_count":11,"citation_normalized_percentile":{"value":0.83938855,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":"6","issue":"1","first_page":"8","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11652","display_name":"Imbalanced Data Classification Techniques","score":0.9940000176429749,"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/T11652","display_name":"Imbalanced Data Classification Techniques","score":0.9940000176429749,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.9276999831199646,"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/T13429","display_name":"Electricity Theft Detection Techniques","score":0.9229000210762024,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/portuguese","display_name":"Portuguese","score":0.7581683993339539},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.7174302339553833},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.706109881401062},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5581541061401367},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5490265488624573},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.47472819685935974},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.46592259407043457},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.13872367143630981},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08806759119033813}],"concepts":[{"id":"https://openalex.org/C35219183","wikidata":"https://www.wikidata.org/wiki/Q5146","display_name":"Portuguese","level":2,"score":0.7581683993339539},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.7174302339553833},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.706109881401062},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5581541061401367},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5490265488624573},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47472819685935974},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.46592259407043457},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.13872367143630981},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08806759119033813},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.3390/bdcc6010008","is_oa":true,"landing_page_url":"https://doi.org/10.3390/bdcc6010008","pdf_url":"https://www.mdpi.com/2504-2289/6/1/8/pdf?version=1641806745","source":{"id":"https://openalex.org/S4210238752","display_name":"Big Data and Cognitive Computing","issn_l":"2504-2289","issn":["2504-2289"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Big Data and Cognitive Computing","raw_type":"journal-article"},{"id":"pmh:oai:comum.rcaap.pt:10400.26/38766","is_oa":false,"landing_page_url":"http://hdl.handle.net/10400.26/38766","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"http://purl.org/coar/resource_type/c_6501"},{"id":"pmh:oai:doaj.org/article:ca2538a0973d43b89c89d1ba184dcf01","is_oa":false,"landing_page_url":"https://doaj.org/article/ca2538a0973d43b89c89d1ba184dcf01","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,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Big Data and Cognitive Computing, Vol 6, Iss 1, p 8 (2022)","raw_type":"article"},{"id":"pmh:oai:mdpi.com:/2504-2289/6/1/8/","is_oa":true,"landing_page_url":"https://dx.doi.org/10.3390/bdcc6010008","pdf_url":null,"source":{"id":"https://openalex.org/S4306400947","display_name":"MDPI (MDPI AG)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210097602","host_organization_name":"Multidisciplinary Digital Publishing Institute (Switzerland)","host_organization_lineage":["https://openalex.org/I4210097602"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nd","license_id":"https://openalex.org/licenses/cc-by-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Big Data and Cognitive Computing; Volume 6; Issue 1; Pages: 8","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.3390/bdcc6010008","is_oa":true,"landing_page_url":"https://doi.org/10.3390/bdcc6010008","pdf_url":"https://www.mdpi.com/2504-2289/6/1/8/pdf?version=1641806745","source":{"id":"https://openalex.org/S4210238752","display_name":"Big Data and Cognitive Computing","issn_l":"2504-2289","issn":["2504-2289"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Big Data and Cognitive Computing","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4225752875.pdf","grobid_xml":"https://content.openalex.org/works/W4225752875.grobid-xml"},"referenced_works_count":12,"referenced_works":["https://openalex.org/W1988301066","https://openalex.org/W2282821441","https://openalex.org/W2396739527","https://openalex.org/W2896457183","https://openalex.org/W2898467812","https://openalex.org/W2963691377","https://openalex.org/W2999309192","https://openalex.org/W3096266342","https://openalex.org/W3198305561","https://openalex.org/W4230765542","https://openalex.org/W4253234135","https://openalex.org/W6739901393"],"related_works":["https://openalex.org/W2912615426","https://openalex.org/W1964944391","https://openalex.org/W2104166387","https://openalex.org/W4299785812","https://openalex.org/W4391101703","https://openalex.org/W563704311","https://openalex.org/W4322721676","https://openalex.org/W2625894112","https://openalex.org/W581688671","https://openalex.org/W2310048306"],"abstract_inverted_index":{"Classification":[0],"problems":[1],"are":[2,85],"common":[3],"activities":[4],"in":[5,17,24,27,38,95,151],"many":[6],"different":[7],"domains":[8],"and":[9,52,92,139],"supervised":[10],"learning":[11],"algorithms":[12],"have":[13],"shown":[14],"great":[15],"promise":[16],"these":[18],"areas.":[19],"The":[20],"classification":[21,78,88,153],"of":[22,55,65,79,154],"goods":[23,80],"international":[25],"trade":[26],"Brazil":[28],"represents":[29],"a":[30,45,56,66,105,116,127],"real":[31],"challenge":[32],"due":[33],"to":[34,44,147],"the":[35,40,49,62,86,132,142,152],"complexity":[36],"involved":[37],"assigning":[39],"correct":[41],"category":[42],"codes":[43,83],"good,":[46],"especially":[47],"considering":[48],"tax":[50,77],"penalties":[51],"legal":[53],"implications":[54],"misclassification.":[57],"This":[58],"work":[59],"focuses":[60],"on":[61,69],"training":[63],"process":[64],"classifier":[67],"based":[68],"bidirectional":[70],"encoder":[71],"representations":[72],"from":[73,103,114],"transformers":[74],"(BERT)":[75],"for":[76,90],"with":[81],"MCN":[82],"which":[84],"official":[87],"system":[89],"import":[91],"export":[93],"products":[94],"Brazil.":[96],"In":[97],"particular,":[98],"this":[99],"article":[100],"presents":[101],"results":[102,113,121],"using":[104,115],"specific":[106],"Portuguese-language-pretrained":[107],"BERT":[108,118],"model,":[109,134],"as":[110,112],"well":[111],"multilingual-pretrained":[117],"model.":[119],"Experimental":[120],"show":[122],"that":[123,141],"Portuguese":[124],"model":[125],"had":[126],"slightly":[128],"better":[129],"performance":[130,150],"than":[131],"multilingual":[133],"achieving":[135],"an":[136],"MCC":[137],"0.8491,":[138],"confirms":[140],"classifiers":[143],"could":[144],"be":[145],"used":[146],"improve":[148],"specialists\u2019":[149],"goods.":[155]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":2}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2022-05-05T00:00:00"}
