{"id":"W3096266342","doi":"10.1007/978-3-030-61377-8_28","title":"BERTimbau: Pretrained BERT Models for Brazilian Portuguese","year":2020,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Topic Modeling","field":"Computer Science","cited_by":598,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Natural language processing; Artificial intelligence; Transformer; Language model; Sentence; Encoder; Portuguese; Transfer of learning; Textual entailment; Named-entity recognition; Logical consequence; Linguistics","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0007552507,0.0006648118,0.0007257988,0.0005448005,0.0002323744,0.0004543343,0.004793234,0.0004302938,0.00001075957],"category_scores_gemma":[0.0001491781,0.0006411715,0.0002644695,0.0004792425,0.0003851264,0.001003216,0.001497004,0.0007529471,0.00002179507],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002583589,"about_ca_system_score_gemma":0.00081582,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000190124,"about_ca_topic_score_gemma":0.00003855459,"domain_scores_codex":[0.9948258,0.00002380076,0.0007489099,0.002460178,0.001089032,0.0008522155],"domain_scores_gemma":[0.9967499,0.0004318216,0.0002997886,0.00183163,0.0003182157,0.0003686573],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001049129,0.00001971531,0.000003399311,0.00007536585,0.00001713391,0.00005677943,0.001018105,0.1321606,0.0001495577,0.1085206,0.00008727958,0.7578809],"study_design_scores_gemma":[0.0002226103,0.0001181228,0.000006411401,0.0001426698,0.000006736633,0.00001840783,7.125085e-8,0.6552728,0.0002268736,0.3425184,0.0009998253,0.0004671118],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00001280685,0.0005960683,0.9876415,0.003522066,0.00169521,0.0009306915,0.00001453876,0.0003243498,0.005262733],"genre_scores_gemma":[0.07136209,0.00003047293,0.9214533,0.005473265,0.0008855305,0.0000375368,0.00001400745,0.00006968385,0.0006741227],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7574138,"threshold_uncertainty_score":0.9996039,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02926096844476913,"score_gpt":0.252910922927005,"score_spread":0.2236499544822358,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}