{"id":"W2135868586","doi":"10.1007/s10115-010-0341-9","title":"Classifier-based acronym extraction for business documents","year":2010,"lang":"en","type":"article","venue":"Knowledge and Information Systems","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":7,"is_retracted":false,"has_abstract":false,"ca_institutions":"École de Technologie Supérieure","funders":"","keywords":"Acronym; Computer science; Classifier (UML); Information extraction; Precision and recall; Natural language processing; Artificial intelligence; Information retrieval; Data mining; Linguistics","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":[0.0002164994,0.00008177895,0.00008775217,0.00004795366,0.0001003468,0.00007162784,0.00006651192,0.0001997974,0.000004194369],"category_scores_gemma":[0.0001356711,0.00006670201,0.00002668023,0.00006185996,0.00005419007,0.00003118622,0.0000193138,0.0000601433,0.00002323574],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000004998281,"about_ca_system_score_gemma":0.00005827527,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000009471749,"about_ca_topic_score_gemma":0.00001388315,"domain_scores_codex":[0.9995133,0.00001317736,0.0002053802,0.00009088847,0.0000569819,0.0001202722],"domain_scores_gemma":[0.9995094,0.00001984087,0.00009009084,0.0001264483,0.0002007977,0.00005341836],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0003763283,0.0001870042,0.006138292,0.00136169,0.0001074406,4.42769e-7,0.0007070455,0.00003318315,0.2743364,0.003513841,0.107815,0.6054233],"study_design_scores_gemma":[0.0006265939,0.00007997183,0.003057865,0.00001709833,0.000006327099,0.000008203177,0.0001472711,0.001451406,0.00558539,0.000006587748,0.9889144,0.00009887177],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.816701,0.001376206,0.1468754,0.000429858,0.006101498,0.000996172,0.00009189217,0.0001194791,0.02730847],"genre_scores_gemma":[0.9979262,0.00003101777,0.0006236242,0.00007641476,0.0002647578,0.00008927946,0.0002352178,0.000004958126,0.0007485044],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8810994,"threshold_uncertainty_score":0.2720029,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01358242975406378,"score_gpt":0.2953081056031392,"score_spread":0.2817256758490755,"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."}}