{"id":"W1828773426","doi":"10.1007/978-3-642-21043-3_23","title":"Correcting Different Types of Errors in Texts","year":2011,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Spelling; Computer science; Punctuation; Natural language processing; Artificial intelligence; Word (group theory); Verb; Error detection and correction; Speech recognition; Linguistics; Algorithm","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005754313,0.0004122687,0.0005633229,0.001089019,0.00007296546,0.0001687211,0.003242562,0.0003027926,0.000013919],"category_scores_gemma":[0.0001500492,0.0003375463,0.00009008754,0.0005886994,0.0004355605,0.0005706236,0.001376281,0.0008810235,0.000005145537],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002090166,"about_ca_system_score_gemma":0.0002403256,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008573176,"about_ca_topic_score_gemma":0.0002320784,"domain_scores_codex":[0.9973097,0.00003223438,0.0005330945,0.00103172,0.0006178457,0.0004754393],"domain_scores_gemma":[0.9981177,0.0002875,0.0003917289,0.000951093,0.0001713636,0.00008058338],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00000567783,0.0000346096,0.0003589942,0.00007337505,0.000004629377,0.00006316549,0.001550318,0.0004567156,0.0003598432,0.01834221,0.000003988106,0.9787465],"study_design_scores_gemma":[0.0002359904,0.0002570989,0.0003969258,0.002194774,0.000008182415,0.0001221748,2.671672e-7,0.06470095,0.06423044,0.8668599,0.00006450259,0.0009287942],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0007130883,0.002094956,0.9944603,0.00009723208,0.000973958,0.0002429279,0.000001384631,0.0001895997,0.001226578],"genre_scores_gemma":[0.5441044,0.00001584444,0.4554079,0.0001942465,0.00007617453,0.000004110625,9.802834e-7,0.00002008593,0.0001762131],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9778177,"threshold_uncertainty_score":0.9999077,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01804613100901811,"score_gpt":0.2580295709324431,"score_spread":0.239983439923425,"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."}}