{"id":"W2140608987","doi":"10.1109/nlpke.2009.5313823","title":"Real-word spelling correction using Google Web 1T n-gram with backoff","year":2009,"lang":"en","type":"article","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":29,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Spelling; n-gram; Computer science; Word (group theory); Set (abstract data type); Edit distance; String (physics); Fraction (chemistry); Error detection and correction; Natural language processing; Matching (statistics); Precision and recall; Subsequence; Artificial intelligence; Information retrieval; Speech recognition; Algorithm; Language model; Mathematics; Statistics; Programming language","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001736518,0.0001472214,0.0001370097,0.0001229924,0.0001170779,0.0002748931,0.0004803552,0.00007420497,0.00001784864],"category_scores_gemma":[0.00001557234,0.0001103076,0.00003266148,0.0006234783,0.00002377094,0.0007077283,0.00005869222,0.0001922929,0.00001932705],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000896598,"about_ca_system_score_gemma":0.00008236335,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002193268,"about_ca_topic_score_gemma":0.00004891895,"domain_scores_codex":[0.9989541,0.00002834368,0.0001571033,0.0003564375,0.0002384467,0.0002655371],"domain_scores_gemma":[0.9993271,0.00002958451,0.00009215031,0.0003858991,0.00009917175,0.0000660459],"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":[0.00007709175,0.0002612695,0.0009511388,0.0000356063,0.00002740223,0.0001842611,0.0008233573,0.0009063049,0.1281033,0.08385175,0.008216068,0.7765625],"study_design_scores_gemma":[0.0003182359,0.0004086736,0.0001977587,0.0002000502,0.00001667219,0.0002996157,0.00004628842,0.8023836,0.1674856,0.02652141,0.001484913,0.0006371895],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0175631,0.0002056696,0.9657949,0.000294119,0.0002683491,0.0001381982,1.751756e-7,0.00162992,0.01410556],"genre_scores_gemma":[0.3956418,0.00001410247,0.6033444,0.0002101385,0.00006431314,6.595639e-7,7.652791e-7,0.00000643252,0.0007173309],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8014773,"threshold_uncertainty_score":0.4498214,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01486304847848152,"score_gpt":0.2766314386383832,"score_spread":0.2617683901599017,"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."}}