{"id":"W2936126040","doi":"10.2196/12310","title":"Word Embedding for the French Natural Language in Health Care: Comparative Study","year":2019,"lang":"en","type":"article","venue":"JMIR Medical Informatics","topic":"Machine Learning in Healthcare","field":"Computer Science","cited_by":25,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Word2vec; Computer science; Natural language processing; Word embedding; Artificial intelligence; Cosine similarity; Similarity (geometry); Embedding; Context (archaeology); Semantic similarity; Natural language; Set (abstract data type); Feature (linguistics); Analogy; Information retrieval; Cluster analysis; Linguistics","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":[0.001097815,0.0001407461,0.0003034917,0.0001030355,0.0001389282,0.00009767769,0.00117437,0.00006970784,0.00003216067],"category_scores_gemma":[0.0001648812,0.00009009702,0.00004804456,0.0004086811,0.00003717587,0.0003003748,0.0003145158,0.0008303805,0.00005424776],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001447877,"about_ca_system_score_gemma":0.000352831,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003652505,"about_ca_topic_score_gemma":0.0005480123,"domain_scores_codex":[0.9978451,0.0001555796,0.0006793639,0.0001403447,0.0007757062,0.0004038959],"domain_scores_gemma":[0.9980795,0.0009361305,0.0002332709,0.0005245286,0.0000731124,0.0001534562],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001099929,0.0001027541,0.01270148,0.0006574676,0.00002303786,0.000004769893,0.8548609,0.0008079577,1.703608e-7,0.001988574,0.003334789,0.1255071],"study_design_scores_gemma":[0.0009948778,0.000325051,0.01635437,0.0001339398,0.000001314045,0.000007253483,0.06886286,0.9074207,0.000001130649,0.00002295649,0.005739498,0.000136061],"study_design_candidate":"qualitative","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9520956,0.001296989,0.03218583,0.006350855,0.00171615,0.005089745,0.000005772821,0.000248624,0.001010414],"genre_scores_gemma":[0.9875451,0.000003579899,0.009784672,0.002314599,0.00007475593,0.0001493143,0.000008992288,0.000005691502,0.000113276],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9066128,"threshold_uncertainty_score":0.367405,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02074335361527897,"score_gpt":0.3948938538819395,"score_spread":0.3741505002666606,"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."}}