{"id":"https://openalex.org/W3211939470","doi":"https://doi.org/10.63317/4v9eufgmyo6q","title":"RoBERTuito: a pre-trained language model for social media text in Spanish","display_name":"RoBERTuito: a pre-trained language model for social media text in Spanish","publication_year":2022,"publication_date":"2022-06-01","ids":{"openalex":"https://openalex.org/W3211939470","doi":"https://doi.org/10.63317/4v9eufgmyo6q","mag":"3211939470"},"language":"en","primary_location":{"id":"doi:10.63317/4v9eufgmyo6q","doi":"https://doi.org/10.63317/4v9eufgmyo6q","is_oa":false,"landing_page_url":"https://doi.org/10.63317/4v9eufgmyo6q","pdf_url":null,"source":{"id":"https://openalex.org/S7407088301","display_name":"Language Resources and Evaluation Conference (LREC)","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Language Resources and Evaluation Conference","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2111.09453","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Juan Manuel P\u00e9rez","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Juan Manuel P\u00e9rez","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020684336","display_name":"Dami\u00e1n Furman","orcid":"https://orcid.org/0000-0003-4570-1364","observed_orcids":["https://orcid.org/0000-0003-4570-1364"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dami\u00e1n Ariel Furman","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056654929","display_name":"Laura Alonso Alemany","orcid":"https://orcid.org/0000-0001-6283-6266","observed_orcids":["https://orcid.org/0000-0001-6283-6266"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Laura Alonso Alemany","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5024585590","display_name":"Franco M. Luque","orcid":"https://orcid.org/0000-0002-5316-2500","observed_orcids":["https://orcid.org/0000-0002-5316-2500"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Franco M. Luque","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":8.7562,"has_fulltext":true,"cited_by_count":97,"citation_normalized_percentile":{"value":0.98497344,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"7235","last_page":"7243"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9872999787330627,"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":0.9872999787330627,"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":0.008500000461935997,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.0010999999940395355,"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/pre-trained-language-models","display_name":"pre-trained language models","score":0.9139999747276306},{"id":"https://openalex.org/keywords/spanish-language","display_name":"Spanish language","score":0.7039999961853027},{"id":"https://openalex.org/keywords/social-media-text","display_name":"social media text","score":0.8690000176429749},{"id":"https://openalex.org/keywords/user-generated-text","display_name":"user-generated text","score":0.9129999876022339},{"id":"https://openalex.org/keywords/tweets","display_name":"tweets","score":0.7590000033378601},{"id":"https://openalex.org/keywords/domain-specific-pre-training","display_name":"domain-specific pre-training","score":0.859000027179718},{"id":"https://openalex.org/keywords/transfer-learning","display_name":"transfer learning","score":0.7990000247955322},{"id":"https://openalex.org/keywords/code-switching","display_name":"code-switching","score":0.7960000038146973},{"id":"https://openalex.org/keywords/multilingual-nlp","display_name":"multilingual NLP","score":0.5479999780654907}],"concepts":[{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.7796176075935364},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7657794952392578},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6711433529853821},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6505110263824463},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6001999974250793},{"id":"https://openalex.org/C518677369","wikidata":"https://www.wikidata.org/wiki/Q202833","display_name":"Social media","level":2,"score":0.5916534066200256},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5330535173416138},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.47045814990997314},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.4652014672756195},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.26747822761535645},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0851677656173706},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"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}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.63317/4v9eufgmyo6q","doi":"https://doi.org/10.63317/4v9eufgmyo6q","is_oa":false,"landing_page_url":"https://doi.org/10.63317/4v9eufgmyo6q","pdf_url":null,"source":{"id":"https://openalex.org/S7407088301","display_name":"Language Resources and Evaluation Conference (LREC)","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Language Resources and Evaluation Conference","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2111.09453","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2111.09453","pdf_url":"https://arxiv.org/pdf/2111.09453","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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:3211939470","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2111.09453v1","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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.2111.09453","doi":"https://doi.org/10.48550/arxiv.2111.09453","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2111.09453","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2111.09453","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2111.09453","pdf_url":"https://arxiv.org/pdf/2111.09453","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3211939470.pdf","grobid_xml":"https://content.openalex.org/works/W3211939470.grobid-xml"},"referenced_works_count":23,"referenced_works":["https://openalex.org/W2041282815","https://openalex.org/W2061554433","https://openalex.org/W2146867136","https://openalex.org/W2468328197","https://openalex.org/W2626778328","https://openalex.org/W2750787240","https://openalex.org/W2787560479","https://openalex.org/W2885185669","https://openalex.org/W2904605268","https://openalex.org/W2923014074","https://openalex.org/W2954226438","https://openalex.org/W2963341956","https://openalex.org/W2965373594","https://openalex.org/W2970377225","https://openalex.org/W2970771982","https://openalex.org/W2990188683","https://openalex.org/W3009095382","https://openalex.org/W3027440908","https://openalex.org/W3032736433","https://openalex.org/W3082274269","https://openalex.org/W3097370230","https://openalex.org/W3160137267","https://openalex.org/W3180918883"],"related_works":["https://openalex.org/W3180918883","https://openalex.org/W4385681388","https://openalex.org/W4281397847","https://openalex.org/W4226516308","https://openalex.org/W4224291642","https://openalex.org/W3097370230","https://openalex.org/W4388676246","https://openalex.org/W3114757058","https://openalex.org/W4394637965","https://openalex.org/W3130812595"],"abstract_inverted_index":{"Since":[0],"BERT":[1],"appeared,":[2],"Transformer":[3],"language":[4,71,99],"models":[5,24,40,58,100,130],"and":[6,123],"transfer":[7],"learning":[8],"have":[9,41],"become":[10],"state-of-the-art":[11],"for":[12,25,52,73,112],"Natural":[13],"Language":[14],"Understanding":[15],"tasks.":[16,50,133],"Recently,":[17],"some":[18,113],"works":[19],"geared":[20],"towards":[21],"pre-training":[22],"specially-crafted":[23],"particular":[26],"domains,":[27],"such":[28,57],"as":[29],"scientific":[30],"papers,":[31],"medical":[32],"documents,":[33],"user-generated":[34,74,91],"texts,":[35],"among":[36],"others.":[37],"These":[38],"domain-specific":[39],"been":[42],"shown":[43],"to":[44,105,153],"improve":[45],"performance":[46,127],"significantly":[47],"in":[48,76,101,131],"most":[49],"However,":[51],"languages":[53],"other":[54,97],"than":[55],"English":[56,132],"are":[59],"not":[60],"widely":[61],"available.":[62],"In":[63,103],"this":[64],"work,":[65],"we":[66,138],"present":[67],"RoBERTuito,":[68],"a":[69,86],"pre-trained":[70,98],"model":[72,108,146],"text":[75,92],"Spanish,":[77],"trained":[78],"on":[79,85],"over":[80],"500":[81],"million":[82],"tweets.":[83],"Experiments":[84],"benchmark":[87,121],"of":[88,116],"tasks":[89,115],"involving":[90],"showed":[93],"that":[94],"RoBERTuito":[95,140],"outperformed":[96],"Spanish.":[102],"addition":[104],"this,":[106],"our":[107],"achieves":[109],"top":[110],"results":[111],"English-Spanish":[114],"the":[117,144,150],"Linguistic":[118],"Code-Switching":[119],"Evaluation":[120],"(LinCE)":[122],"has":[124],"also":[125],"competitive":[126],"against":[128],"monolingual":[129],"To":[134],"facilitate":[135],"further":[136],"research,":[137],"make":[139],"publicly":[141],"available":[142],"at":[143],"HuggingFace":[145],"hub":[147],"together":[148],"with":[149],"dataset":[151],"used":[152],"pre-train":[154],"it.":[155]},"counts_by_year":[{"year":2026,"cited_by_count":15},{"year":2025,"cited_by_count":19},{"year":2024,"cited_by_count":34},{"year":2023,"cited_by_count":24},{"year":2022,"cited_by_count":5}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2021-11-22T00:00:00"}