{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009448367,0.000262781,0.000348457,0.0001657996,0.0007308853,0.0001969701,0.0008312623,0.0000901787,0.00004275625],"category_scores_gemma":[0.00005985647,0.0001923867,0.00006294572,0.0008360614,0.0001966533,0.001007438,0.0002894972,0.001037154,0.000001623046],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002099002,"about_ca_system_score_gemma":0.0004507974,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000132624,"about_ca_topic_score_gemma":0.000195752,"domain_scores_codex":[0.9960237,0.0003647097,0.0008898695,0.000401206,0.001828509,0.0004920624],"domain_scores_gemma":[0.9984742,0.0003903721,0.0003807577,0.0004491049,0.0001236176,0.0001819017],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001520369,0.0007846802,0.002536374,0.00001519538,0.0001026897,0.000007937771,0.06844915,0.9172246,0.000006680933,0.0006879364,0.0001091965,0.009923478],"study_design_scores_gemma":[0.003893659,0.0001699874,0.002847992,0.00004093038,0.00002856911,0.00002067517,0.01875884,0.9738712,9.445664e-7,0.00009138797,0.00003034935,0.0002454927],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3023744,0.00001896516,0.695545,0.0004443865,0.0001551651,0.001055056,0.00001394239,0.0001223177,0.000270812],"genre_scores_gemma":[0.7518649,0.000002568313,0.2465481,0.0003426976,0.00004152218,0.0009982318,0.0001492001,0.00001537178,0.00003734896],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.4494905,"threshold_uncertainty_score":0.7845303,"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."}}