{"id":"W4220799018","doi":"10.1016/j.artmed.2022.102282","title":"Chinese clinical named entity recognition via multi-head self-attention based BiLSTM-CRF","year":2022,"lang":"en","type":"article","venue":"Artificial Intelligence in Medicine","topic":"Topic Modeling","field":"Computer Science","cited_by":132,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Saskatchewan","funders":"Natural Science Foundation of Hunan Province","keywords":"Computer science; Conditional random field; Artificial intelligence; Named-entity recognition; Natural language processing; Benchmark (surveying); Task (project management); Feature (linguistics); Deep learning; Embedding; Character (mathematics); Pattern recognition (psychology)","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001858659,0.001044566,0.001108242,0.002349488,0.0007999177,0.0007732113,0.001322221,0.001384766,0.00412763],"category_scores_gemma":[0.003256462,0.0004484485,0.001530175,0.002507955,0.0003424111,0.00170028,0.001362143,0.00149722,0.003081129],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007731841,"about_ca_system_score_gemma":0.002403827,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01431418,"about_ca_topic_score_gemma":0.01822995,"domain_scores_codex":[0.9986059,0.000246771,0.0001780085,0.0006542933,0.0001434549,0.0001716043],"domain_scores_gemma":[0.9981864,0.0007901746,0.0001529721,0.0002569231,0.000525883,0.00008758158],"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":[0.001337258,0.0005081152,0.03486744,0.001260974,0.0005031955,0.0016421,0.000500135,0.03502751,0.03036074,0.005582504,0.09148392,0.7969261],"study_design_scores_gemma":[0.0001156336,0.0002467635,0.02987013,0.0001219714,0.0008420948,0.001713102,0.0001762466,0.9047862,0.02434338,0.0120411,0.02559163,0.0001517406],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.158275,0.008927933,0.7729542,0.002821879,0.001611578,0.0005935335,0.02781195,0.01741393,0.009589937],"genre_scores_gemma":[0.7642004,0.001910932,0.1824202,0.000746178,0.0007933076,0.0003955432,0.04035206,0.000487256,0.008694112],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01431418,"threshold_uncertainty_score":0.02846169,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1429093938694033,"score_gpt":0.4090009094470708,"score_spread":0.2660915155776675,"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."}}