{"id":"W2996350961","doi":"10.1186/s12911-019-0980-z","title":"Improving clinical named entity recognition in Chinese using the graphical and phonetic feature","year":2019,"lang":"en","type":"article","venue":"BMC Medical Informatics and Decision Making","topic":"Topic Modeling","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"University of Manchester","keywords":"Computer science; Natural language processing; Artificial intelligence; Feature (linguistics); Named-entity recognition; Pinyin; Chinese characters; Embedding; Information retrieval; Linguistics","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002356478,0.0001126944,0.0002245417,0.0001196647,0.00009674914,0.0002598297,0.0003536303,0.0001891452,0.00001398827],"category_scores_gemma":[0.0009674078,0.00006872764,0.0000498453,0.0002761885,0.00006967137,0.0004535753,0.0005934724,0.000480155,0.000005431303],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001255948,"about_ca_system_score_gemma":0.00009649232,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001256838,"about_ca_topic_score_gemma":0.0000629991,"domain_scores_codex":[0.9982842,0.00008383904,0.0006476067,0.0001892438,0.0005963953,0.0001986729],"domain_scores_gemma":[0.9976742,0.001663574,0.0001706973,0.000321838,0.00004313652,0.0001265462],"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":[0.00001944231,0.00001901129,0.04620825,0.0000821972,0.000003413179,0.000004504609,0.0005512127,0.0001402277,0.000004430561,0.0005596521,0.00001606641,0.9523916],"study_design_scores_gemma":[0.0006386039,0.00002275242,0.009078476,0.0003025561,0.000003290953,0.00006095355,0.000128095,0.9806124,4.99139e-7,0.009031894,0.00002568531,0.00009478071],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5088657,0.00009682773,0.4906297,0.00002695667,0.0002409228,0.00009377354,2.549965e-7,0.00001209905,0.00003381943],"genre_scores_gemma":[0.6448444,0.0000597452,0.3545654,0.000477915,0.0000464287,0.000001543493,4.882812e-7,0.000002879507,0.000001187282],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9804722,"threshold_uncertainty_score":0.2802632,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04025595392247056,"score_gpt":0.3433896400771219,"score_spread":0.3031336861546514,"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."}}