{"id":"W2154507487","doi":"10.63317/44fpr4ygd2xg","title":"New Tools for Web-Scale N-grams","year":2010,"lang":"en","type":"article","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":74,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Ambiguity; n-gram; Set (abstract data type); Scale (ratio); Natural language processing; Annotation; World Wide Web; Information retrieval; Web resource; Artificial intelligence; Resource (disambiguation); 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":[0.00350907,0.002052113,0.001699033,0.007681786,0.001776598,0.004551347,0.002465602,0.001583487,0.01920028],"category_scores_gemma":[0.03037625,0.001536796,0.001600995,0.008296991,0.001157651,0.01191317,0.004568752,0.003469606,0.01565609],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001005882,"about_ca_system_score_gemma":0.001603326,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001573285,"about_ca_topic_score_gemma":0.003762955,"domain_scores_codex":[0.9958286,0.0008465679,0.0008202886,0.00062141,0.001756989,0.0001262206],"domain_scores_gemma":[0.9856619,0.007401186,0.001338153,0.003077699,0.002153077,0.0003678499],"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":[0.0005118055,0.0002351376,0.002583312,0.001001914,0.0001672714,0.0006759741,0.001250905,0.006004995,0.01783699,0.0918187,0.08125754,0.7966556],"study_design_scores_gemma":[0.0001702169,0.00009133964,0.001965284,0.0004543995,0.00008681643,0.00140476,0.000530979,0.2168489,0.02869097,0.3079382,0.4415115,0.0003066173],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.001834969,0.0003603074,0.9254246,0.0003686762,0.00017792,0.0002226559,0.003064485,0.06490006,0.003646291],"genre_scores_gemma":[0.01393301,0.0002810374,0.9709367,0.0001989576,0.0001384434,0.0004279797,0.005287899,0.005787515,0.003008469],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01920028,"threshold_uncertainty_score":0.0642314,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01365188499041967,"score_gpt":0.2777855487621568,"score_spread":0.2641336637717371,"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."}}