{"id":"W4386576650","doi":"10.18653/v1/2023.rail-1.1","title":"Automatic Spell Checker and Correction for Under-represented Spoken Languages: Case Study on Wolof","year":2023,"lang":"en","type":"article","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université du Québec à Montréal","funders":"","keywords":"Computer science; Spell; Natural language processing; Annotation; Lexicon; Levenshtein distance; Artificial intelligence; Focus (optics); 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":[0.002430774,0.0007060257,0.0006513272,0.002356697,0.001481199,0.001288156,0.001060994,0.0008020652,0.00306275],"category_scores_gemma":[0.01969513,0.0002661679,0.0002932115,0.001911092,0.001390314,0.002418892,0.001910674,0.0009263402,0.001290137],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005774428,"about_ca_system_score_gemma":0.001917184,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006606127,"about_ca_topic_score_gemma":0.009309019,"domain_scores_codex":[0.9963779,0.001340647,0.0005060786,0.0007542649,0.0007944835,0.0002266494],"domain_scores_gemma":[0.9807994,0.01172218,0.001670569,0.002719028,0.002746811,0.0003420105],"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":[0.001096511,0.0002071891,0.03900195,0.002229484,0.00008954496,0.01394679,0.03673437,0.007329785,0.1073783,0.009598896,0.01689858,0.7654886],"study_design_scores_gemma":[0.0001687024,0.0007190591,0.04873715,0.001260178,0.0002532567,0.03410933,0.04161531,0.1153134,0.4235224,0.01962426,0.3138923,0.0007846952],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.7841553,0.001045511,0.1929264,0.001011848,0.0002036113,0.0002748441,0.003790453,0.01005278,0.006539259],"genre_scores_gemma":[0.8320009,0.0003216577,0.1585847,0.0001797517,0.00003114699,0.00009322036,0.003375611,0.001668153,0.003744957],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.006606127,"threshold_uncertainty_score":0.01313537,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03423147737888139,"score_gpt":0.35078985138778,"score_spread":0.3165583740088986,"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."}}