{"id":"W6947978898","doi":"10.48448/8pz8-t445","title":"Automatic Spell Checker and Correction for Under-represented Spoken Languages: Case Study on Wolof","year":2023,"lang":"en","type":"other","venue":"Underline Science Inc.","topic":"Musicology and Musical Analysis","field":"Arts and Humanities","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université du Québec à Montréal","funders":"","keywords":"Spell; Lexicon; Levenshtein distance; Annotation; Focus (optics); Spoken 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002523865,0.000736037,0.0006079421,0.00252175,0.001379567,0.001353851,0.001071428,0.0007657252,0.003666441],"category_scores_gemma":[0.0187672,0.0002510738,0.0002914178,0.001970646,0.001307503,0.002340347,0.002126425,0.0008319087,0.001606851],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005391277,"about_ca_system_score_gemma":0.001851072,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006610177,"about_ca_topic_score_gemma":0.009164836,"domain_scores_codex":[0.9965008,0.001302207,0.0004904688,0.0007437752,0.0007456334,0.0002170356],"domain_scores_gemma":[0.9826335,0.01061399,0.001458541,0.00249426,0.002465954,0.0003337329],"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":[0.001051055,0.0001973653,0.03758148,0.001985329,0.00008440303,0.01178421,0.03020696,0.006305594,0.0858736,0.00791703,0.01888503,0.7981279],"study_design_scores_gemma":[0.0001888312,0.0006873193,0.05201811,0.001272116,0.0002450939,0.02816264,0.04232651,0.1297211,0.3754915,0.01813603,0.3510053,0.0007454613],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.7670421,0.00110121,0.2037467,0.001042208,0.0002278434,0.0003219866,0.004671752,0.01363025,0.008215946],"genre_scores_gemma":[0.8231136,0.0003237964,0.1653953,0.0001866326,0.00003465908,0.0001044916,0.004416119,0.001959092,0.004466328],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.006610177,"threshold_uncertainty_score":0.01334769,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06395711718248887,"score_gpt":0.334659742653968,"score_spread":0.2707026254714792,"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."}}