{"id":"W4224303302","doi":"10.2196/37804","title":"Conditional Probability Joint Extraction of Nested Biomedical Events: Design of a Unified Extraction Framework Based on Neural Networks","year":2022,"lang":"en","type":"article","venue":"JMIR Medical Informatics","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":17,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Natural Science Foundation of China","keywords":"Computer science; Event (particle physics); Artificial intelligence; Conditional random field; Biomedical text mining; Joint probability distribution; Machine learning; Natural language processing; Data mining; Text mining; Mathematics","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001743192,0.001524654,0.0009079679,0.002430547,0.0006451074,0.001329718,0.002392942,0.001454077,0.002880573],"category_scores_gemma":[0.003053661,0.0007456843,0.001620798,0.001359318,0.0007718653,0.003210158,0.001874693,0.00185743,0.00110815],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001797747,"about_ca_system_score_gemma":0.00258707,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01682338,"about_ca_topic_score_gemma":0.02532269,"domain_scores_codex":[0.99915,0.0001125365,0.0000709879,0.0003962968,0.0001683698,0.0001016674],"domain_scores_gemma":[0.9991096,0.0003428543,0.0001070838,0.00009213114,0.0002952605,0.00005308275],"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":[0.0002801618,0.000263636,0.004199593,0.0002828583,0.0002589341,0.0005828508,0.0002564919,0.3508577,0.02261618,0.02759502,0.008165479,0.584641],"study_design_scores_gemma":[0.000005428685,0.00001717535,0.0003236096,0.00001263234,0.00003495361,0.000047835,0.0000144179,0.9866245,0.003947526,0.007549397,0.001411813,0.00001072364],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00621593,0.0001756931,0.9898499,0.0002021164,0.00002225849,0.0001063247,0.0002181439,0.002290869,0.0009186562],"genre_scores_gemma":[0.2381183,0.0005102639,0.752112,0.0004017712,0.00007686007,0.0004223988,0.002384519,0.000345522,0.005628273],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01682338,"threshold_uncertainty_score":0.0334509,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03417981275461371,"score_gpt":0.3165629690061541,"score_spread":0.2823831562515404,"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."}}