{"id":"W3109919947","doi":"10.2196/22508","title":"Identification of Semantically Similar Sentences in Clinical Notes: Iterative Intermediate Training Using Multi-Task Learning","year":2020,"lang":"en","type":"article","venue":"JMIR Medical Informatics","topic":"Topic Modeling","field":"Computer Science","cited_by":32,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Computer science; Task (project management); Identification (biology); Natural language processing; Training (meteorology); Artificial intelligence; Engineering","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006093662,0.002954082,0.001152106,0.001864924,0.001331711,0.001681596,0.003316917,0.002636407,0.002354901],"category_scores_gemma":[0.0193094,0.0008664436,0.002328674,0.001224072,0.001273899,0.00355712,0.004421824,0.005183173,0.001951469],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001468234,"about_ca_system_score_gemma":0.002563832,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005943497,"about_ca_topic_score_gemma":0.008689156,"domain_scores_codex":[0.9956863,0.001702207,0.0003305399,0.001558534,0.0003977315,0.0003246389],"domain_scores_gemma":[0.9853495,0.01034248,0.0005567943,0.001372581,0.001812029,0.0005666977],"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":[0.001484182,0.002031368,0.01808807,0.0008314184,0.0004520551,0.0012127,0.002074925,0.134932,0.02557234,0.002108771,0.01700676,0.7942055],"study_design_scores_gemma":[0.0001207199,0.0006441438,0.002106412,0.00007899251,0.0001107361,0.0002859879,0.0005271587,0.9728727,0.01401379,0.006988471,0.002184327,0.00006659339],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2692855,0.001610868,0.7084036,0.00130266,0.0004319555,0.001088674,0.001498991,0.01276731,0.003610393],"genre_scores_gemma":[0.7374456,0.0002738328,0.2505531,0.0009698808,0.0001363149,0.0009106204,0.006905677,0.0004032712,0.002401714],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006093662,"threshold_uncertainty_score":0.03222674,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1071406895850211,"score_gpt":0.3789297631923781,"score_spread":0.271789073607357,"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."}}