{"id":"W2130987418","doi":"10.1109/wi.2005.79","title":"Integrating Compound Terms in Bayesian Text Classification","year":2005,"lang":"en","type":"article","venue":"","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"","keywords":"Computer science; Smoothing; Word (group theory); Artificial intelligence; Natural language processing; Bayesian probability; Term (time); Representation (politics); Naive Bayes classifier; Compound; Component (thermodynamics); Machine learning; Mathematics; 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":[0.0001777167,0.00009532572,0.00009415135,0.0002099665,0.00006423796,0.0002047061,0.0007730108,0.00006663433,0.00005505182],"category_scores_gemma":[0.00004250395,0.00007828,0.00002649728,0.000449724,0.00004573248,0.0008149467,0.0001138787,0.0001352104,0.0001761114],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009743211,"about_ca_system_score_gemma":0.00002189199,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001836214,"about_ca_topic_score_gemma":0.000146531,"domain_scores_codex":[0.9990936,0.00002535158,0.0002666973,0.0002903492,0.0001409697,0.0001830636],"domain_scores_gemma":[0.9993176,0.00005749255,0.00007730911,0.0004934832,0.00002322218,0.00003082766],"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":[6.022478e-7,0.00004127969,0.004245098,0.000001443384,0.000001140148,6.656698e-7,0.0001785108,0.000006123649,0.00253857,0.6137891,0.001011154,0.3781863],"study_design_scores_gemma":[0.0007592986,0.00007711258,0.1037878,0.00004250752,0.000002428704,0.00001744855,0.001229268,0.7360078,0.01959032,0.05509267,0.08281805,0.0005752846],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01103708,0.00003183944,0.8972653,0.01955795,0.00007933703,0.0001453181,2.378161e-7,0.0008232354,0.07105971],"genre_scores_gemma":[0.8768519,0.000008082496,0.1218,0.0002807592,0.0000210981,0.00002312215,0.00000189237,0.000003666196,0.001009515],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8658147,"threshold_uncertainty_score":0.3192165,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02413243508252776,"score_gpt":0.2743366962494589,"score_spread":0.2502042611669311,"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."}}