{"id":"W2036430923","doi":"10.3115/1699648.1699670","title":"Real-word spelling correction using Google Web IT 3-grams","year":2009,"lang":"en","type":"article","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":94,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa","funders":"Natural Sciences and Engineering Research Council of Canada; University of Toronto","keywords":"Spelling; Computer science; Word (group theory); Fraction (chemistry); Set (abstract data type); String (physics); Task (project management); Natural language processing; Artificial intelligence; Precision and recall; Error detection and correction; Matching (statistics); String searching algorithm; Edit distance; Recall; Speech recognition; Pattern matching; Mathematics; Algorithm; Statistics","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":[0.001101426,0.002125211,0.001186704,0.006562154,0.0007551523,0.00108522,0.001217984,0.001091757,0.002388366],"category_scores_gemma":[0.009555987,0.0003257885,0.0008469691,0.004974095,0.0004044061,0.001601334,0.001001787,0.0008668561,0.004089658],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004554485,"about_ca_system_score_gemma":0.001509346,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007791705,"about_ca_topic_score_gemma":0.01410947,"domain_scores_codex":[0.9971092,0.0004432012,0.000437822,0.0006121758,0.001226272,0.0001713631],"domain_scores_gemma":[0.9906749,0.00164883,0.002231899,0.001984806,0.003261964,0.0001975803],"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":[0.0006879267,0.0001539041,0.02055587,0.0008082276,0.0002203874,0.00075092,0.0004091073,0.004816485,0.08486474,0.001001949,0.01792916,0.8678012],"study_design_scores_gemma":[0.0001364569,0.0006988588,0.06109506,0.0002535057,0.0003951387,0.004519304,0.0008256563,0.2924009,0.5625437,0.007442616,0.06913318,0.0005555925],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2998894,0.003060408,0.581268,0.000628843,0.001144328,0.0006169843,0.01713596,0.08930779,0.006948303],"genre_scores_gemma":[0.3740547,0.0008066817,0.5991301,0.0002231447,0.0002405562,0.0002683963,0.01745362,0.002201784,0.005620941],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007791705,"threshold_uncertainty_score":0.01549268,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0233433113406875,"score_gpt":0.3014352583549979,"score_spread":0.2780919470143104,"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."}}