{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001650102,0.002332276,0.001646675,0.005470092,0.001109478,0.001153475,0.001572747,0.001204792,0.003299282],"category_scores_gemma":[0.01123887,0.0004348829,0.001080067,0.003968152,0.0005944748,0.001533647,0.001174574,0.001187383,0.00565073],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006022344,"about_ca_system_score_gemma":0.001965306,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008104238,"about_ca_topic_score_gemma":0.01735411,"domain_scores_codex":[0.9959226,0.0006672519,0.0005272261,0.0009599341,0.001695915,0.0002270749],"domain_scores_gemma":[0.989868,0.001821134,0.001570127,0.002400387,0.004120935,0.0002193809],"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":[0.001016971,0.0002884609,0.01138909,0.0008648154,0.0002895382,0.0007229122,0.0003694925,0.008069435,0.0956709,0.0008783123,0.0163595,0.8640806],"study_design_scores_gemma":[0.0001803152,0.0007508652,0.02681244,0.0001960405,0.000331928,0.003002951,0.000521426,0.3802263,0.5363652,0.003889533,0.04722763,0.0004953336],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2051084,0.002208085,0.692383,0.0005097432,0.00114217,0.0006699381,0.00886381,0.08491266,0.00420214],"genre_scores_gemma":[0.2324906,0.0004947743,0.7486522,0.0001902242,0.0002285888,0.0003710494,0.01066958,0.002285878,0.004617052],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.008104238,"threshold_uncertainty_score":0.01611412,"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."}}