{"id":"W4391129997","doi":"10.1109/ictc58733.2023.10392770","title":"Uncertainty-based Active Learning with Ensemble Technique for Enhancing the Performance of Natural Language Classification with Limited Data","year":2023,"lang":"en","type":"article","venue":"","topic":"Machine Learning and Algorithms","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"Korea Institute for Advancement of Technology; National Research Foundation","keywords":"Computer science; Machine learning; Artificial intelligence; Natural language; Ensemble learning; Preprocessor; Natural language understanding; Data pre-processing; Language model; Training set; Data 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":[0.004434976,0.001022986,0.001800204,0.001220356,0.0006711128,0.0009062189,0.002193132,0.001287768,0.0008334551],"category_scores_gemma":[0.008203289,0.0003376247,0.001076318,0.001128708,0.000710518,0.003012202,0.001515215,0.002064122,0.000294866],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004236347,"about_ca_system_score_gemma":0.0006388431,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002344449,"about_ca_topic_score_gemma":0.002420396,"domain_scores_codex":[0.9984477,0.0005918102,0.000107868,0.0002769413,0.0004505418,0.0001251777],"domain_scores_gemma":[0.9940646,0.003936141,0.0002797097,0.0004952599,0.001080406,0.0001439266],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0003558896,0.0003863453,0.004451965,0.0001062499,0.000213266,0.000157078,0.0003650881,0.5192679,0.0146906,0.008418861,0.003442682,0.448144],"study_design_scores_gemma":[0.00000224186,0.00002265996,0.00008683036,0.000001866587,0.000007678659,0.00000861136,0.000006055972,0.9972627,0.001202218,0.001257923,0.0001369568,0.000004256583],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03414593,0.0005940049,0.9636666,0.0002244764,0.00006593128,0.00002921983,0.00004390538,0.0005659738,0.0006639109],"genre_scores_gemma":[0.7939314,0.0004246206,0.2030739,0.0003233888,0.0002193354,0.0001306427,0.0003616375,0.0001093176,0.001425795],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004434976,"threshold_uncertainty_score":0.02345467,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02072955563730382,"score_gpt":0.2796560352480592,"score_spread":0.2589264796107554,"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."}}