{"id":"W2142742813","doi":"","title":"Learning from multiple partially observed views - an application to multilingual text categorization","year":2009,"lang":"en","type":"preprint","venue":"NPARC","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":274,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Computer science; Artificial intelligence; Leverage (statistics); Categorization; Machine learning; Natural language processing; Generalization; Text categorization; Set (abstract data type); Training set; Supervised learning; Artificial neural network; Mathematics","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004723601,0.0008028169,0.001922352,0.001695621,0.0009681313,0.002045695,0.002167351,0.002009852,0.001276881],"category_scores_gemma":[0.02130318,0.0005661816,0.001641518,0.002484338,0.00141766,0.003935613,0.002788011,0.002574,0.0005233674],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00131182,"about_ca_system_score_gemma":0.0007067282,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002197972,"about_ca_topic_score_gemma":0.002217289,"domain_scores_codex":[0.9968234,0.001548613,0.0001582067,0.000685739,0.000615775,0.0001682928],"domain_scores_gemma":[0.9819584,0.01208247,0.001298294,0.003036444,0.001250696,0.0003737239],"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":[0.0005738136,0.0002970904,0.01349335,0.0003846415,0.0005663804,0.001017653,0.00116333,0.3169044,0.00836513,0.05157679,0.006719757,0.5989377],"study_design_scores_gemma":[0.00002169243,0.00007696205,0.001324535,0.0000275074,0.00004751883,0.0002452997,0.000109719,0.9244691,0.003172743,0.06845555,0.002017877,0.00003153715],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02946595,0.0005994254,0.9681234,0.0005193119,0.00003547188,0.00004889567,0.00019099,0.0004421311,0.000574526],"genre_scores_gemma":[0.5818497,0.0006119032,0.4129444,0.0002925304,0.000296497,0.000207254,0.001802647,0.0001567289,0.001838237],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004723601,"threshold_uncertainty_score":0.02498102,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0694166084151494,"score_gpt":0.2987423463949583,"score_spread":0.2293257379798089,"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."}}