{"id":"W2150417504","doi":"","title":"Creating Robust Supervised Classifiers via Web-Scale N-Gram Data","year":2010,"lang":"en","type":"article","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":33,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"n-gram; Bracketing (phenomenology); Computer science; Artificial intelligence; Scale (ratio); Natural language processing; Gram; Noun; Verb; Speech recognition; Language model","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":[0.004813968,0.001312297,0.001713037,0.001995189,0.001050741,0.001668281,0.001535707,0.002009416,0.002306962],"category_scores_gemma":[0.02099027,0.000377388,0.0007661441,0.001707243,0.0006934389,0.00511852,0.001899214,0.0020281,0.004806243],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005969555,"about_ca_system_score_gemma":0.001306345,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001290819,"about_ca_topic_score_gemma":0.00284807,"domain_scores_codex":[0.9956105,0.001707724,0.0002874289,0.0009486885,0.001222406,0.0002232578],"domain_scores_gemma":[0.9827632,0.01021668,0.001091325,0.002985712,0.002631303,0.0003118899],"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":[0.001051603,0.001018943,0.0128145,0.000509056,0.0002751583,0.000320835,0.0001575016,0.09088639,0.02287366,0.003018258,0.01863522,0.8484389],"study_design_scores_gemma":[0.00006652615,0.000198762,0.002155731,0.00005308983,0.00005281804,0.0001772015,0.0001701485,0.9505898,0.0323846,0.007523115,0.006582401,0.00004581542],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2410011,0.0016642,0.7258127,0.0008252587,0.0006202235,0.0006063096,0.00357723,0.01740797,0.008485139],"genre_scores_gemma":[0.5343362,0.0004029653,0.448977,0.0005677342,0.0003758576,0.0007261612,0.01081761,0.0005884689,0.003207994],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004813968,"threshold_uncertainty_score":0.02545899,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03026958532982212,"score_gpt":0.2801285670039378,"score_spread":0.2498589816741157,"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."}}