{"id":"W4385456320","doi":"10.1145/3611651","title":"Pre-trained Language Models in Biomedical Domain: A Systematic Survey","year":2023,"lang":"en","type":"review","venue":"ACM Computing Surveys","topic":"Topic Modeling","field":"Computer Science","cited_by":166,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal; Mila - Quebec Artificial Intelligence Institute","funders":"Chinese University of Hong Kong","keywords":"Computer science; Biomedical text mining; Terminology; Domain (mathematical analysis); Data science; Artificial intelligence; Taxonomy (biology); Health informatics; Natural language processing; Health care; Text mining","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":[0.004771274,0.001883302,0.001600748,0.002943032,0.0003206068,0.001747499,0.002521386,0.001521377,0.003981092],"category_scores_gemma":[0.01914512,0.000669295,0.001698137,0.002537996,0.0007269297,0.004969407,0.001292374,0.00242612,0.004393734],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001048359,"about_ca_system_score_gemma":0.003419675,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004579239,"about_ca_topic_score_gemma":0.005595107,"domain_scores_codex":[0.9978679,0.000875172,0.0002339107,0.0004606401,0.0004763331,0.00008608099],"domain_scores_gemma":[0.9868866,0.01082045,0.0002591549,0.000491971,0.001414084,0.0001276851],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"systematic_review","study_design_scores_codex":[0.0000994507,0.0001386111,0.0021424,0.007444938,0.0002548828,0.0001078459,0.000207333,0.009304167,0.00121835,0.005934558,0.03132462,0.9418229],"study_design_scores_gemma":[0.0001184902,0.001168748,0.0102832,0.0194543,0.001750185,0.00240067,0.001266687,0.1756724,0.01136099,0.05265699,0.7234914,0.0003758891],"study_design_candidate":"systematic_review","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.006596919,0.8005201,0.1708498,0.008034397,0.001394507,0.0002736709,0.001899643,0.002122497,0.008308328],"genre_scores_gemma":[0.07229783,0.8029664,0.09756134,0.005436184,0.002611283,0.00060734,0.009911335,0.0006840419,0.007924158],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.004771274,"threshold_uncertainty_score":0.02523321,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1191560848007357,"score_gpt":0.3643785811444352,"score_spread":0.2452224963436995,"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."}}