{"id":"W6939068694","doi":"10.60692/v5y4c-kkk74","title":"MasakhaPOS: Part-of-Speech Tagging for Typologically Diverse African languages","year":2023,"lang":"en","type":"article","venue":"Greater South Information System","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Mila - Quebec Artificial Intelligence Institute","funders":"","keywords":"Conditional random field; Transfer (computing); Baseline (sea); Transfer of learning; Training set; Field (mathematics); Languages of Africa","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":[0.001080448,0.0008209238,0.0004105222,0.002697978,0.00143468,0.0008486579,0.0008507756,0.0007260899,0.008193879],"category_scores_gemma":[0.002403236,0.0003471692,0.0005083658,0.00218944,0.0004806891,0.001832771,0.002497413,0.000954337,0.005331371],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005194849,"about_ca_system_score_gemma":0.001184901,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006586264,"about_ca_topic_score_gemma":0.01452689,"domain_scores_codex":[0.9993016,0.0001796541,0.00007891919,0.0002409347,0.0001021597,0.00009671863],"domain_scores_gemma":[0.9988289,0.0003816933,0.000148495,0.0003359894,0.0001806385,0.0001242522],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.003817364,0.0006431042,0.113868,0.004110424,0.0003946526,0.002833746,0.007027846,0.007794343,0.09571309,0.01382174,0.361603,0.3883726],"study_design_scores_gemma":[0.000439727,0.0004009078,0.1821508,0.0005506524,0.0002097941,0.002815754,0.008063222,0.02834861,0.0512733,0.01654936,0.7089414,0.0002564332],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"dataset","genre_gemma":"methods","genre_scores_codex":[0.4452717,0.001655952,0.0389896,0.001037385,0.0006691884,0.0005290085,0.4742523,0.01345619,0.02413856],"genre_scores_gemma":[0.2763617,0.000463555,0.05952176,0.0003818865,0.0000895823,0.001022385,0.6543103,0.001109222,0.006739642],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.008193879,"threshold_uncertainty_score":0.02741128,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04539049895815687,"score_gpt":0.2646086308393963,"score_spread":0.2192181318812395,"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."}}