{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0002786719,0.0004030032,0.0003527395,0.0007908057,0.000214365,0.0009153111,0.001997246,0.0002166293,0.00001035778],"category_scores_gemma":[0.00005931951,0.0003309493,0.00004392147,0.0004422117,0.0006513168,0.0007698623,0.0009681394,0.000409807,0.000034874],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002200055,"about_ca_system_score_gemma":0.0001305719,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000163431,"about_ca_topic_score_gemma":0.00007893862,"domain_scores_codex":[0.9971776,0.00001271203,0.0003747858,0.001329383,0.0006413484,0.0004641695],"domain_scores_gemma":[0.9981154,0.0001527283,0.000244047,0.001165479,0.0001835475,0.000138858],"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":[0.000006674187,0.00001451145,0.0001090537,0.00001997236,0.000007935797,0.000007272812,0.0004667649,0.0003121438,0.002033468,0.03507657,0.00001856003,0.9619271],"study_design_scores_gemma":[0.00296965,0.002989779,0.01185908,0.002722674,0.00006356771,0.0002637852,0.00002636486,0.6407598,0.05942282,0.214587,0.05841686,0.005918653],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0009618523,0.0002221395,0.9926618,0.003229161,0.0005109177,0.0004930624,0.000004351512,0.0003742082,0.001542505],"genre_scores_gemma":[0.6589085,0.00008226762,0.3381351,0.0009865506,0.0001589343,0.00005002037,0.000004236188,0.00002761368,0.001646756],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9560084,"threshold_uncertainty_score":0.9999142,"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."}}