{"id":"W3022964795","doi":"10.2196/17637","title":"Multi-Level Representation Learning for Chinese Medical Entity Recognition: Model Development and Validation","year":2020,"lang":"en","type":"article","venue":"JMIR Medical Informatics","topic":"Machine Learning in Healthcare","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Natural Science Foundation of China","keywords":"Computer science; Natural language processing; Artificial intelligence; Softmax function; Language model; Deep learning; Feature learning; Named-entity recognition; Representation (politics); Encoder; Information retrieval; Task (project management)","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":[0.0008801252,0.0001439026,0.000206228,0.00006898329,0.000233024,0.0001167012,0.0004495229,0.0002060971,0.00005569257],"category_scores_gemma":[0.00359506,0.0001245687,0.00003972045,0.0002772396,0.00005003957,0.0006840947,0.0003454571,0.0005589059,0.00004059981],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003811568,"about_ca_system_score_gemma":0.0004213318,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005797157,"about_ca_topic_score_gemma":0.000006768118,"domain_scores_codex":[0.997593,0.00008792197,0.0007261061,0.0001993902,0.001151296,0.0002422333],"domain_scores_gemma":[0.9985619,0.0002775003,0.000230614,0.0001544873,0.0001770905,0.0005984246],"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":[0.00002922106,0.00009497761,0.01143352,0.001294684,0.00003269265,0.000008874496,0.06015167,0.001801195,0.000006894519,0.0009484807,0.001136148,0.9230617],"study_design_scores_gemma":[0.0008450319,0.00005396034,0.002075673,0.000077228,0.000002726787,0.00001592961,0.0002192206,0.994984,0.00005045862,0.0002452561,0.001282216,0.0001482843],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1371516,0.00001237107,0.8563727,0.005640618,0.0001051088,0.0003843753,0.000002330622,0.0002013832,0.000129541],"genre_scores_gemma":[0.3197006,0.00002915896,0.675923,0.003798111,0.0001555785,0.0001643295,0.0001728504,0.00001236624,0.00004400985],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9931828,"threshold_uncertainty_score":0.5079765,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1171216017315767,"score_gpt":0.3830128472133887,"score_spread":0.265891245481812,"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."}}