{"id":"W4404782906","doi":"10.18653/v1/2024.emnlp-main.251","title":"Voices Unheard: NLP Resources and Models for Yorùbá Regional Dialects","year":2024,"lang":"en","type":"article","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Canadian Institute for Advanced Research; National Science Foundation","keywords":"Natural language processing; Computer science; Artificial intelligence; Yoruba; Linguistics; 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":[0.00075369,0.0005295163,0.0004118546,0.0005626986,0.000734547,0.00145594,0.0009049381,0.0007077074,0.008644782],"category_scores_gemma":[0.003117962,0.0004155116,0.000561509,0.0006711351,0.0003976245,0.002052936,0.001209027,0.0008936942,0.001935402],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001054155,"about_ca_system_score_gemma":0.001022688,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.08771104,"about_ca_topic_score_gemma":0.1338023,"domain_scores_codex":[0.999823,0.00008748298,0.00001026837,0.00004291217,0.00001865902,0.00001759804],"domain_scores_gemma":[0.9994233,0.0003954082,0.00001838032,0.0000704554,0.00007249873,0.00001995513],"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":[0.001487455,0.0002924769,0.02288834,0.0007749447,0.0003821864,0.001437359,0.004813419,0.3742349,0.007741345,0.07288107,0.1178086,0.3952579],"study_design_scores_gemma":[0.00009535162,0.00003698378,0.004994124,0.00009123192,0.00008519262,0.0001689266,0.001511523,0.9139897,0.002467675,0.03121584,0.04530232,0.00004112984],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3952491,0.006121217,0.4873688,0.006524302,0.0004487603,0.0003652726,0.04637241,0.02015268,0.03739757],"genre_scores_gemma":[0.8244544,0.001252074,0.1222926,0.0002694114,0.00006500224,0.0004405944,0.03468909,0.001358728,0.0151782],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.08771104,"threshold_uncertainty_score":0.174401,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02528236940543752,"score_gpt":0.2852018835029734,"score_spread":0.2599195140975358,"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."}}