{"id":"W4385572106","doi":"10.18653/v1/2023.semeval-1.7","title":"BERTastic at SemEval-2023 Task 3: Fine-Tuning Pretrained Multilingual Transformers Does Order Matter?","year":2023,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Computer science; Transformer; Artificial intelligence; Fine-tuning; SemEval; Deep learning; Language model; Natural language processing; Machine learning; Framing (construction); Task (project management)","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":[0.003104746,0.002987785,0.001221634,0.001081606,0.0008034173,0.001784188,0.002503807,0.002105372,0.007985864],"category_scores_gemma":[0.009473803,0.0006683265,0.001347326,0.0009870215,0.0007250251,0.00424572,0.001801765,0.004098631,0.005426776],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001309849,"about_ca_system_score_gemma":0.001541787,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01046106,"about_ca_topic_score_gemma":0.02398901,"domain_scores_codex":[0.9987889,0.000360455,0.00007287515,0.0004960534,0.0001389258,0.0001427774],"domain_scores_gemma":[0.9974427,0.001145859,0.0001182055,0.0006993389,0.0004036023,0.0001903024],"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":[0.003173141,0.001478809,0.01509265,0.001287851,0.0006890482,0.0006102702,0.0004667205,0.1075232,0.03314274,0.006165302,0.1317791,0.6985913],"study_design_scores_gemma":[0.0004915989,0.0008237801,0.005777518,0.0001417348,0.0002046002,0.0003429401,0.0003601752,0.9076243,0.04364722,0.01281957,0.02765318,0.0001133147],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5908489,0.007611724,0.2714753,0.00352119,0.002062325,0.0007471943,0.0212028,0.07318011,0.02935047],"genre_scores_gemma":[0.7987657,0.0006401754,0.1287503,0.001199365,0.0002725232,0.0003930691,0.0521883,0.002079614,0.01571101],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01046106,"threshold_uncertainty_score":0.02671534,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01810490949344891,"score_gpt":0.2628011679382798,"score_spread":0.2446962584448309,"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."}}