{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003687956,0.001000879,0.0006942839,0.002735056,0.0005741642,0.0014858,0.0007742686,0.0005680767,0.002025737],"category_scores_gemma":[0.01108004,0.0001976567,0.001232106,0.003098853,0.0003846729,0.003348173,0.001303298,0.0007291127,0.001222478],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008974368,"about_ca_system_score_gemma":0.001551244,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01613044,"about_ca_topic_score_gemma":0.01114819,"domain_scores_codex":[0.9978886,0.0007012654,0.0002769756,0.0006365132,0.0003518283,0.0001447416],"domain_scores_gemma":[0.9942992,0.003432323,0.0004161428,0.0006176402,0.001110728,0.0001239289],"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":[0.0007135833,0.0002163892,0.08961926,0.0007409358,0.0004044298,0.0008586481,0.001006221,0.04518095,0.01566616,0.003874431,0.01117541,0.8305436],"study_design_scores_gemma":[0.00007774349,0.0002769801,0.08540117,0.0001482412,0.0009182552,0.0009856396,0.000864663,0.8286107,0.05220168,0.009026212,0.02128806,0.0002006006],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.5482379,0.003177468,0.4239677,0.002867364,0.0004196532,0.000460611,0.00733759,0.005293926,0.008237657],"genre_scores_gemma":[0.8717777,0.001079608,0.1158698,0.0001880452,0.000106307,0.0001215858,0.008316227,0.0001261395,0.002414593],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.01613044,"threshold_uncertainty_score":0.03207314,"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."}}