{"id":"W2043419849","doi":"10.3166/ria.18.111-137","title":"L'UMLS entre langue et ontologie : une approche pragmatique dans le domaine médical","year":2004,"lang":"fr","type":"article","venue":"Revue d intelligence artificielle","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Unified Medical Language System; Philosophy; Linguistics; Humanities; Computer science; Natural language processing","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0007014007,0.0004046402,0.0004390752,0.0000646061,0.0002478377,0.00006791909,0.0006194278,0.0008446873,0.0001633993],"category_scores_gemma":[0.0006079509,0.0003910222,0.0002627829,0.0004051029,0.001211369,0.00001335908,0.0002854725,0.0005510403,0.0003728153],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001001559,"about_ca_system_score_gemma":0.0004964062,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001037834,"about_ca_topic_score_gemma":0.0008180931,"domain_scores_codex":[0.9972441,0.000253085,0.0006658346,0.000832629,0.000218617,0.0007857116],"domain_scores_gemma":[0.9985318,0.0001307467,0.0001974018,0.0007360075,0.0001171375,0.0002868633],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0002933042,0.003811759,0.0005911674,0.0009807232,0.0004550536,0.0006925689,0.01376984,0.02789083,0.2988249,0.2171518,0.02531029,0.4102278],"study_design_scores_gemma":[0.0003736288,0.0007732759,0.0001599802,0.0004283088,0.00006224141,0.0003763232,0.01051171,0.00161465,0.4678296,0.01002937,0.5071748,0.0006660367],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.09137014,0.01675534,0.8216968,0.04554934,0.000988879,0.0004413267,0.0000633261,0.0001157018,0.02301913],"genre_scores_gemma":[0.9367192,0.002788151,0.02959585,0.001261236,0.0005869127,0.00007403187,0.0002421135,0.00006337322,0.02866911],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8453491,"threshold_uncertainty_score":0.9998541,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02777079375492197,"score_gpt":0.2925595196639217,"score_spread":0.2647887259089997,"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."}}