{"id":"W1845278523","doi":"10.1007/3-540-70659-3_58","title":"Document Classification Using Phrases","year":2002,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Natural language processing; Computer science; Artificial intelligence; Grammar; Classifier (UML); Naive Bayes classifier; Bayes classifier; Pattern recognition (psychology); Linguistics; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001115835,0.001567133,0.001395004,0.007907696,0.001168752,0.003183104,0.001158244,0.0009448968,0.01940743],"category_scores_gemma":[0.003899721,0.0004362583,0.001729714,0.007909016,0.0005759639,0.003514812,0.001491737,0.001376796,0.02378039],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000589299,"about_ca_system_score_gemma":0.0009869726,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001127069,"about_ca_topic_score_gemma":0.001348983,"domain_scores_codex":[0.9986066,0.0002234221,0.0002020132,0.0003943276,0.0004724678,0.0001011391],"domain_scores_gemma":[0.9982409,0.0006689404,0.0001065445,0.0003291172,0.00058126,0.00007315889],"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":[0.00015458,0.00009363759,0.000960238,0.000529138,0.00009963811,0.0001200878,0.00009508795,0.00125713,0.02114435,0.007030455,0.02995442,0.9385611],"study_design_scores_gemma":[0.0001767667,0.001250539,0.007917932,0.0009073509,0.001093477,0.003332669,0.0007288844,0.2455394,0.1847755,0.1001708,0.4538551,0.0002514735],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01935606,0.007537655,0.9186376,0.0009195436,0.001541129,0.0009769253,0.01005949,0.01392184,0.02704974],"genre_scores_gemma":[0.1038679,0.005134176,0.8179616,0.0004838452,0.001012481,0.0009200961,0.02439059,0.0009229488,0.04530628],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01940743,"threshold_uncertainty_score":0.0649243,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04930136608321829,"score_gpt":0.2785514953889736,"score_spread":0.2292501293057553,"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."}}