{"id":"https://openalex.org/W3074221917","doi":"https://doi.org/10.18653/v1/2020.wmt-1.90","title":"Lite Training Strategies for Portuguese-English and English-Portuguese Translation","display_name":"Lite Training Strategies for Portuguese-English and English-Portuguese Translation","publication_year":2020,"publication_date":"2020-01-01","ids":{"openalex":"https://openalex.org/W3074221917","doi":"https://doi.org/10.18653/v1/2020.wmt-1.90","mag":"3074221917"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2020.wmt-1.90","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2020.wmt-1.90","pdf_url":"https://aclanthology.org/2020.wmt-1.90.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Fifth Conference on Machine Translation","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2020.wmt-1.90.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5103141176","display_name":"Alexandre Lopes","orcid":"https://orcid.org/0000-0002-1871-180X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Alexandre Lopes","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030647281","display_name":"Rodrigo Nogueira","orcid":"https://orcid.org/0000-0002-2600-6035"},"institutions":[{"id":"https://openalex.org/I181391015","display_name":"Universidade Estadual de Campinas (UNICAMP)","ror":"https://ror.org/04wffgt70","country_code":"BR","type":"education","lineage":["https://openalex.org/I181391015"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Rodrigo Nogueira","raw_affiliation_strings":["Universidade Estadual de Campinas (UNICAMP), Campinas, Brazil"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universidade Estadual de Campinas (UNICAMP), Campinas, Brazil","institution_ids":["https://openalex.org/I181391015"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087970571","display_name":"Roberto Lotufo","orcid":"https://orcid.org/0000-0002-5652-0852"},"institutions":[{"id":"https://openalex.org/I181391015","display_name":"Universidade Estadual de Campinas (UNICAMP)","ror":"https://ror.org/04wffgt70","country_code":"BR","type":"education","lineage":["https://openalex.org/I181391015"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Roberto Lotufo","raw_affiliation_strings":["Universidade Estadual de Campinas (UNICAMP), Campinas, Brazil"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universidade Estadual de Campinas (UNICAMP), Campinas, Brazil","institution_ids":["https://openalex.org/I181391015"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5065725754","display_name":"H\u00e9lio Pedrini","orcid":"https://orcid.org/0000-0003-0125-630X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Helio Pedrini","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"833","last_page":"840"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9998999834060669,"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/T10028","display_name":"Topic Modeling","score":0.9998999834060669,"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":0.9998999834060669,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9936000108718872,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/portuguese","display_name":"Portuguese","score":0.8890345692634583},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7896658182144165},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.7015665173530579},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6304596662521362},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.599663496017456},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.5750178098678589},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.5502052307128906},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5297544598579407},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.5012876987457275},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.49896693229675293},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.49138393998146057},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.2518370449542999},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.12911760807037354},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.07287880778312683},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.06867676973342896}],"concepts":[{"id":"https://openalex.org/C35219183","wikidata":"https://www.wikidata.org/wiki/Q5146","display_name":"Portuguese","level":2,"score":0.8890345692634583},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7896658182144165},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.7015665173530579},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6304596662521362},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.599663496017456},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.5750178098678589},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.5502052307128906},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5297544598579407},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.5012876987457275},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.49896693229675293},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.49138393998146057},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.2518370449542999},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.12911760807037354},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.07287880778312683},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.06867676973342896},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C105580179","wikidata":"https://www.wikidata.org/wiki/Q188928","display_name":"Messenger RNA","level":3,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.18653/v1/2020.wmt-1.90","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2020.wmt-1.90","pdf_url":"https://aclanthology.org/2020.wmt-1.90.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Fifth Conference on Machine Translation","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2008.08769","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2008.08769","pdf_url":"https://arxiv.org/pdf/2008.08769","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"mag:3074221917","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2008.08769.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.2008.08769","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2008.08769","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.18653/v1/2020.wmt-1.90","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2020.wmt-1.90","pdf_url":"https://aclanthology.org/2020.wmt-1.90.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Fifth Conference on Machine Translation","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G158325759","display_name":null,"funder_award_id":"310828/2018-0","funder_id":"https://openalex.org/F4320322025","funder_display_name":"Conselho Nacional de Desenvolvimento Cient\u00edfico e Tecnol\u00f3gico"},{"id":"https://openalex.org/G2286822848","display_name":null,"funder_award_id":"2018-0","funder_id":"https://openalex.org/F4320322025","funder_display_name":"Conselho Nacional de Desenvolvimento Cient\u00edfico e Tecnol\u00f3gico"}],"funders":[{"id":"https://openalex.org/F4320322025","display_name":"Conselho Nacional de Desenvolvimento Cient\u00edfico e Tecnol\u00f3gico","ror":"https://ror.org/03swz6y49"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3074221917.pdf","grobid_xml":"https://content.openalex.org/works/W3074221917.grobid-xml"},"referenced_works_count":16,"referenced_works":["https://openalex.org/W630532510","https://openalex.org/W1625582487","https://openalex.org/W2130942839","https://openalex.org/W2481265265","https://openalex.org/W2795467683","https://openalex.org/W2806482312","https://openalex.org/W2889326796","https://openalex.org/W2890007195","https://openalex.org/W2899771611","https://openalex.org/W2922709902","https://openalex.org/W2958953787","https://openalex.org/W2963341956","https://openalex.org/W2963403868","https://openalex.org/W2964308564","https://openalex.org/W2970331417","https://openalex.org/W3104526121"],"related_works":["https://openalex.org/W3119821683","https://openalex.org/W2963460546","https://openalex.org/W2970999217","https://openalex.org/W3142584950","https://openalex.org/W2251265917","https://openalex.org/W3196383184","https://openalex.org/W3171986718","https://openalex.org/W2913659301","https://openalex.org/W3096266342","https://openalex.org/W3164871893","https://openalex.org/W3181014475","https://openalex.org/W3183419084","https://openalex.org/W2758724354","https://openalex.org/W3033862527","https://openalex.org/W2576021677","https://openalex.org/W2985215540","https://openalex.org/W3047631559","https://openalex.org/W2250793660","https://openalex.org/W2761791183","https://openalex.org/W3105719633"],"abstract_inverted_index":{"Despite":[0],"the":[1,23,45,59,77,87,94,98,109],"widespread":[2],"adoption":[3],"of":[4,25,47,58,86],"deep":[5],"learning":[6],"for":[7,35,138],"machine":[8],"translation,":[9],"it":[10],"is":[11],"still":[12],"expensive":[13],"to":[14,62,76,93,97,108,124],"develop":[15],"high-quality":[16],"translation":[17,39],"models.In":[18],"this":[19],"work,":[20],"we":[21],"investigate":[22],"use":[24,46],"pre-trained":[26],"models,":[27],"such":[28,66],"as":[29,67,90,92],"T5":[30],"(Raffel":[31],"et":[32],"al.,":[33],"2019)":[34],"Portuguese-English":[36],"and":[37,49,54,70,81,143],"English-Portuguese":[38],"tasks":[40],"using":[41],"low-cost":[42],"hardware.We":[43],"explore":[44],"Portuguese":[48,64],"English":[50,60],"pretrained":[51],"language":[52],"models":[53,75,119,126,142],"propose":[55],"an":[56],"adaptation":[57],"tokenizer":[61],"represent":[63],"characters,":[65],"diaeresis,":[68],"acute":[69],"grave":[71],"accents.We":[72],"compare":[73],"our":[74,106,118],"Google":[78],"Translate":[79],"API":[80],"MarianMT":[82],"on":[83,130],"a":[84,121],"subset":[85],"ParaCrawl":[88],"dataset,":[89],"well":[91],"winning":[95],"submission":[96,107],"WMT19":[99],"Biomedical":[100,111],"Translation":[101,112],"Shared":[102,113],"Task.We":[103],"also":[104],"describe":[105],"WMT20":[110],"Task.Our":[114],"results":[115],"show":[116],"that":[117],"have":[120],"competitive":[122],"performance":[123],"state-of-the-art":[125],"while":[127],"being":[128],"trained":[129],"modest":[131],"hardware":[132],"(a":[133],"single":[134],"8GB":[135],"gaming":[136],"GPU":[137],"nine":[139],"days).Our":[140],"data,":[141],"code":[144],"are":[145],"available":[146],"at":[147],"https://github.com/":[148],"unicamp-dl/Lite-T5-Translation.":[149]},"counts_by_year":[{"year":2022,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2020-08-24T00:00:00"}