{"id":"W3101513017","doi":"10.18653/v1/2020.clinicalnlp-1.15","title":"MeDAL: Medical Abbreviation Disambiguation Dataset for Natural Language Understanding Pretraining","year":2020,"lang":"en","type":"preprint","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":23,"is_retracted":false,"has_abstract":true,"ca_institutions":"Mila - Quebec Artificial Intelligence Institute; McGill University","funders":"","keywords":"Computer science; Natural language processing; Medal; Artificial intelligence; Domain (mathematical analysis); Natural language; Natural (archaeology)","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":[],"consensus_categories":[],"category_scores_codex":[0.0007777875,0.0002040227,0.0002588374,0.00008622417,0.00009394592,0.0002922614,0.001121026,0.0002399902,0.00004764199],"category_scores_gemma":[0.0009061877,0.0001888624,0.00009181803,0.0001127967,0.00002138816,0.0003200765,0.001175596,0.0005288614,0.000007728594],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002048372,"about_ca_system_score_gemma":0.0002427643,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006280934,"about_ca_topic_score_gemma":0.00006973685,"domain_scores_codex":[0.9978232,0.00007271663,0.0003935656,0.0007537525,0.0007090248,0.0002477881],"domain_scores_gemma":[0.9987625,0.0003269626,0.0001871424,0.0005484771,0.0000347251,0.0001401952],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00004507843,0.00007873261,0.0001550848,0.001832645,0.0003030736,0.00006008012,0.02063918,0.002411257,0.0003235241,0.5647936,0.02798361,0.3813742],"study_design_scores_gemma":[0.0002925551,0.0000148799,0.00002424423,0.0001806735,0.00001750663,0.000003537245,0.0002994666,0.9859374,0.00006268992,0.01272031,0.0002242025,0.000222556],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.000342282,0.0002522165,0.9884684,0.00835129,0.001311498,0.0005210371,0.0002047453,0.0002683841,0.0002801191],"genre_scores_gemma":[0.8646802,0.00001261946,0.1284682,0.001281145,0.0004871926,0.00005680139,0.004963617,0.00001727047,0.00003288644],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9835261,"threshold_uncertainty_score":0.7701585,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1476165516358032,"score_gpt":0.3630807248595844,"score_spread":0.2154641732237812,"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."}}