{"id":"W4360989137","doi":"10.18280/ria.370130","title":"NeRBERT- A Biomedical Named Entity Recognition Tagger","year":2023,"lang":"fr","type":"article","venue":"Revue d intelligence artificielle","topic":"Topic Modeling","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Natural language processing; Computer science; Named-entity recognition; Artificial intelligence; Linguistics; Engineering; Philosophy","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","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.001435429,0.0003245159,0.0003705201,0.0003696103,0.0003429497,0.000382948,0.001083316,0.0003416677,0.001744331],"category_scores_gemma":[0.0006500891,0.000370892,0.00025563,0.002657082,0.0003554859,0.0007317485,0.0005968453,0.0005504705,0.03022688],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001486674,"about_ca_system_score_gemma":0.0002080495,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000419678,"about_ca_topic_score_gemma":0.00004830711,"domain_scores_codex":[0.996121,0.0002472512,0.0009234507,0.00109622,0.0005454597,0.001066655],"domain_scores_gemma":[0.9976219,0.0004045785,0.000199911,0.001117971,0.0002663574,0.0003893091],"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":[0.0000104185,0.0003315362,0.0001157573,0.0002874999,0.00004092136,0.0003126375,0.00524635,0.007952058,0.002518991,0.02344401,0.01552529,0.9442145],"study_design_scores_gemma":[0.00005107762,0.0001001316,0.00003778993,0.0004296857,0.00002250298,0.00008378107,0.0004493372,0.8359421,0.007844836,0.01849856,0.1361675,0.0003726879],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05005461,0.001654725,0.9087051,0.02518669,0.009507813,0.0004288494,0.00003253526,0.0005664844,0.003863187],"genre_scores_gemma":[0.8218269,0.002746541,0.03266148,0.00133867,0.002779454,0.0001527289,0.0001605279,0.0001051539,0.1382285],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9438418,"threshold_uncertainty_score":0.9998743,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1211531754063805,"score_gpt":0.3075580413155105,"score_spread":0.1864048659091299,"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."}}