{"id":"W1993301141","doi":"10.1145/1645953.1646205","title":"Real-word spelling correction using Google web 1Tn-gram data set","year":2009,"lang":"en","type":"article","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":40,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa","funders":"","keywords":"n-gram; Computer science; Spelling; Word (group theory); Set (abstract data type); Precision and recall; String (physics); Edit distance; Natural language processing; Error detection and correction; Matching (statistics); Fraction (chemistry); Data set; Artificial intelligence; String searching algorithm; String metric; Information retrieval; Pattern matching; Algorithm; Mathematics; Language model; Statistics; Programming language","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":[0.002167397,0.002613639,0.001612412,0.009845657,0.001300988,0.001169133,0.001741099,0.001575983,0.002195565],"category_scores_gemma":[0.02041401,0.000371296,0.001126365,0.007771371,0.0006019082,0.001972565,0.001404613,0.001264395,0.005063293],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008810582,"about_ca_system_score_gemma":0.002170596,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01606338,"about_ca_topic_score_gemma":0.02581757,"domain_scores_codex":[0.9925242,0.001290305,0.001285749,0.001349391,0.003253056,0.0002972999],"domain_scores_gemma":[0.9775123,0.00504958,0.00282596,0.004799181,0.00939655,0.0004164468],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.001423834,0.0005765253,0.03967268,0.00240253,0.0005250009,0.001822769,0.000772185,0.01230803,0.08787284,0.0007915749,0.0520136,0.7998185],"study_design_scores_gemma":[0.0002742348,0.001127708,0.1039306,0.0003232147,0.0004996996,0.004227017,0.001303689,0.3149752,0.4899441,0.00349382,0.07906217,0.0008384533],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6296915,0.003580118,0.1922066,0.0008384446,0.00176338,0.001242287,0.07311647,0.0892106,0.008350637],"genre_scores_gemma":[0.4599033,0.000800662,0.4196639,0.0002551457,0.0002557891,0.0007285968,0.1106056,0.002362267,0.005424781],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01606338,"threshold_uncertainty_score":0.0319398,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05859422628538493,"score_gpt":0.3450595133657176,"score_spread":0.2864652870803327,"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."}}