{"id":"W4224226311","doi":"10.2196/35606","title":"Multi-Label Classification in Patient-Doctor Dialogues With the RoBERTa-WWM-ext + CNN (Robustly Optimized Bidirectional Encoder Representations From Transformers Pretraining Approach With Whole Word Masking Extended Combining a Convolutional Neural Network) Model: Named Entity Study","year":2022,"lang":"en","type":"article","venue":"JMIR Medical Informatics","topic":"Topic Modeling","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Key Research and Development Program of China","keywords":"Computer science; Encoder; Sentence; Transformer; Natural language processing; Artificial intelligence; Convolutional neural network; Chatbot; F1 score","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":[0.000932281,0.0007716689,0.0003793824,0.0005875138,0.000376132,0.0005171325,0.000957719,0.001076202,0.00145595],"category_scores_gemma":[0.001435799,0.0002761521,0.0007762501,0.0003329856,0.0002907307,0.0009296684,0.0007679581,0.001050648,0.0006322662],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008772694,"about_ca_system_score_gemma":0.0007208315,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007984833,"about_ca_topic_score_gemma":0.01138015,"domain_scores_codex":[0.9995503,0.00009918699,0.00002470582,0.0001874585,0.00005734063,0.00008110614],"domain_scores_gemma":[0.9994831,0.0002320492,0.00006145029,0.0000599431,0.0001119544,0.00005141404],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.001495189,0.0009737265,0.02919084,0.0002140899,0.0002314789,0.0009934979,0.001033832,0.1886639,0.05057481,0.003211865,0.008598766,0.7148181],"study_design_scores_gemma":[0.000007692935,0.00007659295,0.001959355,0.000004910021,0.00002724414,0.00004144801,0.0000486795,0.9891922,0.007370735,0.0006851181,0.0005744296,0.00001159696],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5054017,0.0007930397,0.483621,0.0008723608,0.0002295723,0.0002043311,0.0007490905,0.004190204,0.003938764],"genre_scores_gemma":[0.9261904,0.00009716745,0.06716695,0.0001885463,0.00007237632,0.0000894831,0.0009574727,0.00005957211,0.005177974],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.007984833,"threshold_uncertainty_score":0.01587671,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06015273699982798,"score_gpt":0.2867855212292952,"score_spread":0.2266327842294672,"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."}}