{"id":"W1525194303","doi":"10.1007/11562382_11","title":"Filtering Contents with Bigrams and Named Entities to Improve Text Classification","year":2005,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Bigram; Computer science; Information retrieval; Call for bids; Window (computing); Artificial intelligence; Measure (data warehouse); Natural language processing; Data mining; World Wide Web; Trigram","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":[0.001248371,0.00179839,0.0017474,0.009150917,0.001489944,0.002382912,0.001041665,0.001507606,0.006643686],"category_scores_gemma":[0.00493288,0.0005064978,0.001496523,0.005901293,0.0004256429,0.003250156,0.001339772,0.001517106,0.01160717],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005071616,"about_ca_system_score_gemma":0.001161719,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003827282,"about_ca_topic_score_gemma":0.006615571,"domain_scores_codex":[0.9987636,0.0001733934,0.0001885523,0.000295075,0.0004386721,0.0001408086],"domain_scores_gemma":[0.9957569,0.001486285,0.0002995168,0.0005694045,0.001641795,0.0002460309],"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":[0.0007633729,0.0004455761,0.00787667,0.0004837063,0.00018437,0.0003812874,0.0002750615,0.002138615,0.1071768,0.001402727,0.02389489,0.8549768],"study_design_scores_gemma":[0.0002046916,0.001291102,0.04849771,0.0004295095,0.001955586,0.002608357,0.001723632,0.5043271,0.3259748,0.01883965,0.0938701,0.0002777629],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.2772203,0.007311761,0.6562559,0.001139753,0.002499565,0.0008133156,0.01091031,0.03173046,0.01211865],"genre_scores_gemma":[0.3556616,0.002444425,0.587374,0.0004984288,0.001258281,0.0004210684,0.02486761,0.002243163,0.02523145],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.009150917,"threshold_uncertainty_score":0.02222532,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02289662892023613,"score_gpt":0.2413735191497738,"score_spread":0.2184768902295377,"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."}}