{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009027429,0.001211053,0.0008981635,0.0005203742,0.0008505856,0.002034405,0.001774372,0.001501129,0.01519735],"category_scores_gemma":[0.004401272,0.0006696854,0.001250112,0.00081598,0.0004539629,0.002201563,0.001067516,0.001811847,0.002444646],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001978866,"about_ca_system_score_gemma":0.001749722,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.07336289,"about_ca_topic_score_gemma":0.08831627,"domain_scores_codex":[0.9997281,0.00009838288,0.00001407802,0.000058155,0.00004917988,0.00005199624],"domain_scores_gemma":[0.9993741,0.0003527912,0.0000390357,0.00008598504,0.0001022637,0.00004588922],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0001779828,0.00006336613,0.001049537,0.0001358946,0.00005235831,0.0001755508,0.0002243216,0.7455327,0.0006086121,0.1708688,0.02407515,0.05703569],"study_design_scores_gemma":[0.00001191836,0.000007856795,0.0002106223,0.00002518172,0.00001329347,0.00002270986,0.00003092013,0.9444594,0.0002106398,0.04464785,0.01034836,0.00001131834],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.08035384,0.003286482,0.7756815,0.00461344,0.0008435063,0.0001623093,0.01007311,0.004093669,0.1208921],"genre_scores_gemma":[0.7494774,0.00198554,0.1289776,0.0004105178,0.0002864029,0.0002636437,0.007433998,0.001927074,0.1092377],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.07336289,"threshold_uncertainty_score":0.1458718,"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."}}