{"id":"W2151752770","doi":"10.1023/b:inrt.0000011209.19643.e2","title":"Augmenting Naive Bayes Classifiers with Statistical Language Models","year":2004,"lang":"en","type":"article","venue":"Information Retrieval","topic":"Topic Modeling","field":"Computer Science","cited_by":247,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Naive Bayes classifier; Artificial intelligence; Computer science; Machine learning; Bayes error rate; Bayes classifier; Bayes' theorem; Classifier (UML); Conditional independence; Bayesian programming; Natural language processing; Pattern recognition (psychology); Bayes factor; Bayesian probability; Support vector machine","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":[0.0001926023,0.00009013081,0.00008838175,0.00009451572,0.0000992097,0.0002317691,0.00028488,0.00004685853,0.00001195911],"category_scores_gemma":[0.0000530533,0.0000753612,0.00001898191,0.000223561,0.00002984456,0.002853663,0.00008076937,0.0001286564,0.00006952407],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009778347,"about_ca_system_score_gemma":0.0001347022,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003422343,"about_ca_topic_score_gemma":0.000002026844,"domain_scores_codex":[0.9990052,0.00001330831,0.0002491017,0.0001175792,0.0004055533,0.000209247],"domain_scores_gemma":[0.9994519,0.0000364254,0.00009963191,0.000247817,0.00008643734,0.00007773283],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0000500416,0.0000207407,0.00007901485,0.00004487525,0.00002641756,0.00002097643,0.01684953,0.1065922,0.0000888289,0.8306463,0.00009249901,0.04548853],"study_design_scores_gemma":[0.001193371,0.0001227641,0.0002708093,0.00004549321,0.000007051784,0.00003632784,0.001092968,0.9835308,0.001609518,0.01132223,0.000528303,0.000240426],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0353856,0.000009743699,0.9577029,0.0002930962,0.0001128778,0.0001169156,0.000006373999,0.0001663557,0.006206165],"genre_scores_gemma":[0.8069105,0.000001161922,0.1926491,0.0003702589,0.00002383956,0.000002295991,0.00001272458,0.000003116669,0.00002708769],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8769385,"threshold_uncertainty_score":0.307314,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01324613556970664,"score_gpt":0.2371975164125819,"score_spread":0.2239513808428753,"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."}}