{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","open_science"],"consensus_categories":[],"category_scores_codex":[0.02741373,0.0007271065,0.003495739,0.0009061659,0.0001228778,0.0003419616,0.005927457,0.0005343798,0.000002720958],"category_scores_gemma":[0.003345757,0.0006121159,0.0004377227,0.002928819,0.00006653782,0.0002241835,0.003107051,0.0008838522,0.0001692995],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00028867,"about_ca_system_score_gemma":0.0005782518,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001469624,"about_ca_topic_score_gemma":0.0004700448,"domain_scores_codex":[0.9833999,0.01087513,0.002284268,0.001471556,0.000963741,0.001005434],"domain_scores_gemma":[0.9875,0.008063326,0.0007847083,0.003320917,0.0001017381,0.0002292802],"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":[0.000001170459,0.0001703512,0.0000613333,0.3452847,0.0003578143,0.0006600386,0.004513907,0.00108649,1.977795e-7,0.002074851,0.0002301329,0.645559],"study_design_scores_gemma":[0.0008314462,0.00008856769,0.0005627735,0.2986264,0.0001517157,0.0002120918,0.00008759584,0.6916824,8.122887e-8,0.004009537,0.001434881,0.002312507],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.0001063752,0.5030972,0.4942265,0.00001874223,0.0008023395,0.00111814,0.00002545217,0.0005716684,0.00003351062],"genre_scores_gemma":[0.004098684,0.9010524,0.0918793,0.0001143656,0.0007984081,0.0002942099,0.0007253304,0.0004229336,0.0006143608],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.6905959,"threshold_uncertainty_score":0.999633,"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."}}