{"id":"W4407588263","doi":"10.54254/2755-2721/2024.20851","title":"Comparative Analysis of Improved Versions of BERT Models on Chinese NLP Tasks","year":2025,"lang":"en","type":"article","venue":"Applied and Computational Engineering","topic":"Topic Modeling","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Earl Haig Secondary School","funders":"","keywords":"Natural language processing; Artificial intelligence; Computer science; Linguistics; Philosophy","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":[0.007308076,0.002378435,0.001597775,0.00198963,0.001000283,0.001457929,0.002562924,0.001727533,0.00357369],"category_scores_gemma":[0.01427457,0.0005933905,0.001299225,0.002386604,0.0006417123,0.005222469,0.001320681,0.002720088,0.001787351],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003944762,"about_ca_system_score_gemma":0.002714845,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.05605328,"about_ca_topic_score_gemma":0.06370008,"domain_scores_codex":[0.9976708,0.001021568,0.000169605,0.0004906274,0.0003674724,0.0002798773],"domain_scores_gemma":[0.9888343,0.007693953,0.0002470293,0.001073886,0.001771662,0.0003790802],"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":[0.002375764,0.0009263518,0.008417529,0.0009109813,0.0006621797,0.0002263665,0.0003950503,0.6209872,0.002264488,0.005856541,0.04617068,0.3108069],"study_design_scores_gemma":[0.00008223506,0.0002938801,0.002661954,0.00003772025,0.000132236,0.00004705293,0.00009667267,0.9901903,0.001243104,0.002211848,0.002954246,0.00004882467],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7728776,0.02579576,0.1245075,0.006926127,0.002216572,0.0005886949,0.01060847,0.01693961,0.03953962],"genre_scores_gemma":[0.9098757,0.003496165,0.04928797,0.0007646668,0.0003915717,0.0003890803,0.02237341,0.0007833858,0.01263811],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.05605328,"threshold_uncertainty_score":0.111454,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.009348161555759269,"score_gpt":0.2372709157784682,"score_spread":0.227922754222709,"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."}}