{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003265804,0.0003073078,0.0003240968,0.0001850471,0.0001879634,0.0004922353,0.001949464,0.0003764007,0.00002914979],"category_scores_gemma":[0.0002953745,0.0003176553,0.0000863537,0.0003365961,0.00003193115,0.0003943325,0.0008508241,0.0005563978,0.0002040651],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001222126,"about_ca_system_score_gemma":0.0001280237,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001576676,"about_ca_topic_score_gemma":0.0001917961,"domain_scores_codex":[0.9975087,0.0001609916,0.0005191137,0.001130961,0.0003735243,0.0003067017],"domain_scores_gemma":[0.9976572,0.00009008375,0.0003894017,0.001542292,0.0001801285,0.0001408943],"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":[0.00001269075,0.0001457746,0.001918054,0.00001359689,0.00001370613,0.000001643771,0.001874234,0.01383519,0.08372882,0.008698211,0.0003018146,0.8894563],"study_design_scores_gemma":[0.0004410162,0.000199671,0.02534932,0.0000572219,0.00002232638,5.945522e-7,0.0001954516,0.7903901,0.06278173,0.09704278,0.02270797,0.000811869],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1029808,0.00004770913,0.8917206,0.001857023,0.0002992431,0.0007943869,0.000006441059,0.001723491,0.0005703304],"genre_scores_gemma":[0.8345945,0.00003468487,0.1642394,0.0001881927,0.000142693,0.0002584111,0.000352822,0.00001834134,0.000170923],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8886444,"threshold_uncertainty_score":0.9999276,"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."}}