{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003747524,0.0001388286,0.0001369434,0.0001204724,0.0001275106,0.0003491786,0.00158337,0.000086238,0.00001955161],"category_scores_gemma":[0.00006058502,0.0001200881,0.00002691658,0.0005603878,0.0000192499,0.001335816,0.000370731,0.0002092942,0.00002702859],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007216901,"about_ca_system_score_gemma":0.00008424259,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003375635,"about_ca_topic_score_gemma":0.00004503766,"domain_scores_codex":[0.9987366,0.00004058686,0.0002022314,0.0005121402,0.0002412816,0.0002671925],"domain_scores_gemma":[0.998572,0.00004270034,0.00009886897,0.001153423,0.00006840382,0.00006460761],"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":[0.00001624258,0.0001230052,0.0002323769,0.0000221791,0.00001493107,0.000104894,0.0004864419,0.00017139,0.06795059,0.01903382,0.04008149,0.8717626],"study_design_scores_gemma":[0.00008743649,0.00005016592,0.00004249795,0.0000537857,0.000007648787,0.0001091531,0.00001792845,0.9582186,0.02647844,0.01243936,0.00223915,0.0002558734],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00606424,0.0003297691,0.9861667,0.0004914026,0.0006019866,0.0001310442,0.000002885343,0.001803708,0.004408281],"genre_scores_gemma":[0.2726703,0.00003939751,0.7262436,0.0002884676,0.0001278551,3.837134e-7,0.00001719611,0.00000699498,0.0006058139],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9580472,"threshold_uncertainty_score":0.489705,"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."}}