{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00005656084,0.00007963261,0.0002292626,0.0002925709,0.00002686714,0.00001062513,0.0001567675,0.00002420679,8.11839e-7],"category_scores_gemma":[0.000004021349,0.00007518543,0.00004790693,0.0006429577,0.00001298885,0.00005880905,0.00007844529,0.00005575327,2.038617e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001055187,"about_ca_system_score_gemma":0.00002421125,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001269589,"about_ca_topic_score_gemma":8.612762e-7,"domain_scores_codex":[0.999463,0.000004133909,0.0001831448,0.0001672032,0.000110926,0.00007159612],"domain_scores_gemma":[0.9995733,0.0001868447,0.00004649326,0.0001306626,0.00003828759,0.00002438491],"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":[0.000002905392,0.00001424565,0.00002384519,0.000008795946,0.0001537716,7.067197e-8,0.0002534907,0.6971494,0.0008469756,0.3008707,0.000001953376,0.0006737831],"study_design_scores_gemma":[0.0001791907,0.000009765095,0.004622146,0.00001109879,0.0000435212,1.078225e-7,0.00001567721,0.9861951,0.0002474465,0.008614804,0.000005159705,0.00005591418],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1566127,0.00003914949,0.8419738,0.00004002634,0.00003293254,0.00005728539,0.000003650421,0.00002370436,0.001216682],"genre_scores_gemma":[0.9431989,0.000001309182,0.05673849,0.00003382526,0.000004632034,0.000006004691,0.000007602184,0.000001506154,0.000007744718],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7865862,"threshold_uncertainty_score":0.3065973,"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."}}