{"id":"W7066217127","doi":"","title":"Improving Transformer Performance for French Clinical Notes Classification Using Mixture of Experts on a Limited Dataset","year":2023,"lang":"en","type":"report","venue":"Open Repository and Bibliography (University of Luxembourg)","topic":"Laser-Plasma Interactions and Diagnostics","field":"Physics and Astronomy","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"","funders":"Fonds de recherche du Québec – Nature et technologies; Natural Sciences and Engineering Research Council of Canada; Fonds de Recherche du Québec - Santé; Institut de Valorisation des Données","keywords":"Transformer; Pattern recognition (psychology); Training set; Feature selection","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004477452,0.002553992,0.00203389,0.003696072,0.0009362873,0.001960186,0.001793141,0.003042097,0.004977955],"category_scores_gemma":[0.01003309,0.0004495132,0.002437185,0.002304613,0.0004014967,0.001976698,0.001646829,0.00176225,0.006625054],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00112468,"about_ca_system_score_gemma":0.002170557,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.03067935,"about_ca_topic_score_gemma":0.03213038,"domain_scores_codex":[0.9974667,0.000809819,0.0002195968,0.0007983739,0.0003422932,0.0003631612],"domain_scores_gemma":[0.9952928,0.002686817,0.0001143211,0.0006834948,0.0009822226,0.0002402333],"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":[0.00373041,0.001353541,0.01807226,0.0009968012,0.001462134,0.000848546,0.000240904,0.04630707,0.01367022,0.0009677198,0.1290716,0.7832789],"study_design_scores_gemma":[0.0006994091,0.0009284063,0.01748151,0.0002924473,0.0008969129,0.001461922,0.00068118,0.9241138,0.02698638,0.004374456,0.02192903,0.0001546263],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.5572274,0.02172713,0.2616944,0.00346308,0.002839865,0.0008609418,0.06523821,0.07380739,0.0131416],"genre_scores_gemma":[0.6520305,0.002790854,0.1663123,0.0009899826,0.0006233604,0.0003623775,0.164592,0.001020087,0.01127849],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.03067935,"threshold_uncertainty_score":0.06100154,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1268968461969892,"score_gpt":0.3556919608260341,"score_spread":0.2287951146290449,"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."}}