{"id":"W57814663","doi":"10.1007/3-540-36618-0_24","title":"Combining Naive Bayes and n-Gram Language Models for Text Classification","year":2003,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Topic Modeling","field":"Computer Science","cited_by":170,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Naive Bayes classifier; Computer science; Artificial intelligence; Machine learning; Bayes error rate; Bayesian programming; Bayes' theorem; n-gram; Smoothing; Conditional independence; Inference; Bayes classifier; Bayes factor; Language model; 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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0007443698,0.0003766372,0.0003936744,0.0004573177,0.0002552962,0.0005098667,0.001518411,0.0002683109,0.000002736986],"category_scores_gemma":[0.00008209869,0.0003592825,0.00007955473,0.0002392573,0.0003206171,0.0006345143,0.0005076752,0.0004362357,0.00000389866],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001538449,"about_ca_system_score_gemma":0.0002086144,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001456013,"about_ca_topic_score_gemma":0.00002215826,"domain_scores_codex":[0.9971417,0.00002720602,0.000403856,0.001430176,0.0005058099,0.0004913007],"domain_scores_gemma":[0.9979719,0.0004722942,0.0002288126,0.001018028,0.0001786591,0.000130301],"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":[0.000002980541,0.00001422087,0.00001382184,0.00004979299,0.000008064621,0.00000997455,0.002623326,0.0334076,0.0001998861,0.2397506,0.00001716125,0.7239026],"study_design_scores_gemma":[0.0001937172,0.00006377576,0.00001048394,0.000140665,0.000004871898,0.0000233527,9.862134e-7,0.7552911,0.0002451456,0.2434206,0.0002918307,0.0003134831],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0001499637,0.0007591881,0.9945446,0.0007575743,0.0008153823,0.0005235774,0.000004858797,0.000126252,0.002318639],"genre_scores_gemma":[0.2512124,0.00003935967,0.7467231,0.001517781,0.0001749844,0.00002499104,0.000005272846,0.00003025474,0.0002718966],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7235891,"threshold_uncertainty_score":0.9998859,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03324207233675179,"score_gpt":0.2656846622277709,"score_spread":0.2324425898910191,"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."}}