{"id":"W3036480066","doi":"10.3233/shti200128","title":"Clinical Abbreviation Disambiguation Using Deep Contextualized Representation","year":2020,"lang":"en","type":"article","venue":"Studies in health technology and informatics","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Calgary","funders":"","keywords":"Computer science; Natural language processing; Word (group theory); Artificial intelligence; Representation (politics); Dimension (graph theory); Principal component analysis; Cluster (spacecraft); Word-sense disambiguation; Annotation; Linguistics; Mathematics","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":[0.0006860763,0.001022491,0.0006937548,0.002686895,0.0005329431,0.001117888,0.001284592,0.0008087021,0.002975856],"category_scores_gemma":[0.003262687,0.0002630863,0.00115793,0.002271686,0.0004774359,0.001830706,0.001864411,0.001286311,0.001740856],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008670011,"about_ca_system_score_gemma":0.001720482,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005870868,"about_ca_topic_score_gemma":0.008449421,"domain_scores_codex":[0.9988732,0.0002300007,0.0001193394,0.0004617024,0.0002045526,0.0001112637],"domain_scores_gemma":[0.9990696,0.0002474282,0.0001324735,0.0002110247,0.0002984432,0.00004105157],"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":[0.000470092,0.0001360511,0.006341146,0.0005525789,0.0001902,0.0009597183,0.0006006972,0.03750275,0.02146386,0.02838919,0.03717571,0.866218],"study_design_scores_gemma":[0.0000617399,0.0001726399,0.005126156,0.000325771,0.0002774799,0.001361051,0.0006070043,0.7696806,0.03335026,0.1073385,0.08154509,0.0001537101],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03959525,0.00194157,0.9361664,0.001045634,0.0005228659,0.0002348869,0.004413514,0.01165035,0.004429468],"genre_scores_gemma":[0.4013331,0.000863804,0.5837858,0.0006503802,0.0002437733,0.0002806244,0.009236858,0.0005025155,0.003103186],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005870868,"threshold_uncertainty_score":0.01167339,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1955026523336191,"score_gpt":0.4839009222379654,"score_spread":0.2883982699043463,"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."}}