{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002112563,0.0001211252,0.0001180407,0.0001101126,0.0001133906,0.0002590728,0.0005268567,0.0000802756,0.00002320835],"category_scores_gemma":[0.00003050311,0.0001040756,0.00004564805,0.0005145913,0.00001561782,0.0006411024,0.00007403323,0.0001717157,0.00003098966],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009114899,"about_ca_system_score_gemma":0.00005414463,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001952395,"about_ca_topic_score_gemma":0.00002790407,"domain_scores_codex":[0.9990352,0.00002738442,0.0001772786,0.000312129,0.0002049428,0.000243074],"domain_scores_gemma":[0.9994039,0.00003023778,0.00008018681,0.0003532294,0.00007451986,0.00005792441],"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":[0.00001194503,0.0001091544,0.0001855394,0.00001331492,0.000008522616,0.00005720925,0.0006551004,0.0002191392,0.1432743,0.04098555,0.01263534,0.8018449],"study_design_scores_gemma":[0.0001349255,0.0001063565,0.00006976549,0.00009411521,0.000007449638,0.0001040064,0.00003411396,0.8195332,0.1410859,0.03600196,0.002445434,0.0003828123],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.009215222,0.0002052181,0.973966,0.0008787097,0.0005510668,0.0001035157,1.330111e-7,0.001552582,0.01352753],"genre_scores_gemma":[0.3976528,0.00002385387,0.6004633,0.0005068997,0.00008740095,4.9863e-7,7.196233e-7,0.000005008421,0.001259572],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.819314,"threshold_uncertainty_score":0.4244081,"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."}}