{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005784825,0.0001034494,0.0001125208,0.00009286632,0.0002090479,0.00005098984,0.0007485129,0.00002848693,0.000002032154],"category_scores_gemma":[0.00008110687,0.0000549094,0.00001690386,0.0007086045,0.00004463195,0.0002474616,0.0001146364,0.000258545,0.000003237152],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000178169,"about_ca_system_score_gemma":0.0001072626,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008470363,"about_ca_topic_score_gemma":0.0001009296,"domain_scores_codex":[0.9990938,0.00007016378,0.0001213456,0.000310369,0.0002092938,0.000195027],"domain_scores_gemma":[0.9987212,0.0003873932,0.0001364236,0.0006262515,0.0001059716,0.00002276602],"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":[0.000654068,0.0001247541,0.003262453,0.0004283541,0.0001560536,0.00001309174,0.007417484,0.2363428,0.3523888,0.003711058,0.0005512525,0.3949498],"study_design_scores_gemma":[0.0002657019,0.0002993622,0.001368346,0.00006702975,0.000006861608,0.000004385671,0.0006075751,0.9198058,0.07713692,0.000003799033,0.0003370261,0.00009714759],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1858138,0.00001027263,0.8124076,0.0008054117,0.00002953466,0.0003719624,0.00000311544,0.0002969468,0.0002613527],"genre_scores_gemma":[0.9474648,0.00000189007,0.05163834,0.00006406497,0.00002625662,0.00007022668,0.00009602513,0.00001079314,0.0006275649],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.761651,"threshold_uncertainty_score":0.223914,"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."}}