{"id":"W2148362501","doi":"10.1017/s1351324904003560","title":"Correcting real-word spelling errors by restoring lexical cohesion","year":2005,"lang":"en","type":"article","venue":"Natural Language Engineering","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":180,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Spelling; Computer science; Cohesion (chemistry); Natural language processing; Lexicon; Artificial intelligence; Word (group theory); Context (archaeology); Precision and recall; Recall; Speech recognition; Linguistics","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00184212,0.00106736,0.001314397,0.003202153,0.0008274391,0.001460037,0.001177863,0.0009905815,0.001872053],"category_scores_gemma":[0.02004284,0.0004655307,0.0005842037,0.002145015,0.0008340934,0.002031855,0.001683447,0.0009360054,0.002065675],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004020141,"about_ca_system_score_gemma":0.00134869,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002295416,"about_ca_topic_score_gemma":0.003877066,"domain_scores_codex":[0.9976606,0.0003889921,0.000352266,0.0006811218,0.0007934201,0.0001235423],"domain_scores_gemma":[0.9816126,0.004229346,0.003581859,0.006255423,0.004041274,0.0002794037],"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":[0.0003397275,0.0003096765,0.01995013,0.0007794987,0.0001545116,0.0008543896,0.001380504,0.008452491,0.1991465,0.002169999,0.005659628,0.760803],"study_design_scores_gemma":[0.0003143809,0.0009583621,0.06800993,0.0002633576,0.0007602337,0.005461934,0.001668554,0.1668825,0.6866637,0.01878779,0.04979327,0.0004359946],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5211197,0.001364591,0.4521361,0.0006001048,0.0004623499,0.0003287003,0.0009890244,0.01849686,0.004502581],"genre_scores_gemma":[0.611146,0.0004590046,0.3816438,0.0001886218,0.0001155009,0.0001112508,0.001559478,0.0011624,0.003613996],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.003202153,"threshold_uncertainty_score":0.0097422,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.005958882391220053,"score_gpt":0.2512037126170917,"score_spread":0.2452448302258716,"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."}}