{"id":"W2162940749","doi":"10.64152/10125/44156","title":"Evaluating automatic detection of misspellings in German","year":2008,"lang":"en","type":"article","venue":"Language learning & technology","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":37,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Spell; Computer science; Edit distance; Natural language processing; German; Artificial intelligence; Competence (human resources); Linguistics; Psychology; Philosophy","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002317805,0.0006464124,0.0005860385,0.002393377,0.0003875086,0.001205491,0.0006518501,0.0006242915,0.001585929],"category_scores_gemma":[0.01998718,0.0002256284,0.0002093714,0.001298868,0.0004410406,0.000970589,0.0007697128,0.0003912913,0.001081739],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000651678,"about_ca_system_score_gemma":0.0008034459,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006001507,"about_ca_topic_score_gemma":0.009983952,"domain_scores_codex":[0.9970676,0.0007844914,0.0004319151,0.0007191747,0.0008364449,0.0001603253],"domain_scores_gemma":[0.978188,0.01352564,0.003057898,0.001294275,0.003469924,0.0004642268],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.002409544,0.0002919427,0.1830513,0.00164789,0.0002441519,0.001353714,0.009892758,0.005376025,0.1393489,0.0009386699,0.005070231,0.6503748],"study_design_scores_gemma":[0.0001694334,0.002529595,0.6099308,0.0001574724,0.0002531045,0.003271033,0.006942137,0.06761536,0.289457,0.0006227555,0.01874699,0.0003043627],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9900095,0.0002976108,0.006138762,0.00003960515,0.00002585381,0.00006421185,0.0005699756,0.001362096,0.001492382],"genre_scores_gemma":[0.9857098,0.0001380768,0.01116678,0.00002826201,0.00000558394,0.00002161891,0.001374399,0.00009676809,0.00145868],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.006001507,"threshold_uncertainty_score":0.01225787,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02104914928922183,"score_gpt":0.3133695975337752,"score_spread":0.2923204482445534,"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."}}