{"id":"W4312925950","doi":"10.2196/39077","title":"German Medical Named Entity Recognition Model and Data Set Creation Using Machine Translation and Word Alignment: Algorithm Development and Validation","year":2022,"lang":"en","type":"article","venue":"JMIR Formative Research","topic":"Topic Modeling","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Bundesministerium für Bildung und Forschung","keywords":"Computer science; Test set; Artificial intelligence; Machine translation; Natural language processing; Named-entity recognition; Set (abstract data type); Data set; Test data; German; Annotation; Data mining; Information retrieval; Programming language","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":[],"consensus_categories":[],"category_scores_codex":[0.002822271,0.00008401065,0.00009978725,0.0002253218,0.000671136,0.0001754298,0.0002860764,0.00004258946,0.00001951083],"category_scores_gemma":[0.00002816777,0.00008499039,0.000006592263,0.0002380212,0.00006323309,0.001460613,0.00100198,0.0002884264,0.000001092607],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001211877,"about_ca_system_score_gemma":0.0001297061,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006643987,"about_ca_topic_score_gemma":0.00001847377,"domain_scores_codex":[0.9979267,0.0003550032,0.0002468286,0.0003531688,0.0009069626,0.0002113684],"domain_scores_gemma":[0.9994079,0.0001098365,0.00006155932,0.000236,0.00007478869,0.000109955],"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":[0.00001139168,0.00004150194,0.0001181884,0.00004946064,0.00001297887,0.000002517958,0.02029041,0.0001238045,0.0001181051,0.0002683177,0.00002818043,0.9789351],"study_design_scores_gemma":[0.0004542577,0.00003117353,0.0003512483,0.00002452066,0.000002731147,0.00002632013,0.000250625,0.995259,0.0002567953,0.002906451,0.0003437304,0.00009308031],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4613119,0.0001409896,0.5377477,0.0004007162,0.00002353699,0.0002723302,0.00003797964,0.00002067303,0.00004408961],"genre_scores_gemma":[0.9060367,0.00009152154,0.0933117,0.00003657899,0.00001812519,0.00006900864,0.0004163443,0.000006256312,0.00001369989],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9951352,"threshold_uncertainty_score":0.5161904,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2205561870171737,"score_gpt":0.4362133696296889,"score_spread":0.2156571826125152,"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."}}