{"id":"W6958375831","doi":"10.60692/2kkx3-hs255","title":"MasakhaPOS: Part-of-Speech Tagging for Typologically Diverse African languages","year":2023,"lang":"en","type":"article","venue":"Greater South Information System","topic":"Cell Image Analysis Techniques","field":"Biochemistry, Genetics and Molecular Biology","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":[0.001073939,0.0008931145,0.0004425641,0.002786079,0.00145498,0.0008970281,0.0008583107,0.0007713546,0.008877113],"category_scores_gemma":[0.002406018,0.0003433028,0.0005775336,0.002134033,0.000501449,0.001753025,0.002569119,0.0009784843,0.005845739],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005285754,"about_ca_system_score_gemma":0.001214279,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006963317,"about_ca_topic_score_gemma":0.01408201,"domain_scores_codex":[0.9992992,0.000170445,0.00008252637,0.0002452121,0.000100511,0.0001020899],"domain_scores_gemma":[0.9988775,0.000355431,0.000139696,0.0003194429,0.0001880187,0.0001199792],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.003809717,0.0005826866,0.1078682,0.004168799,0.0004078393,0.002973114,0.00651707,0.006747641,0.1042062,0.01297085,0.3756746,0.3740733],"study_design_scores_gemma":[0.0003896133,0.0003588335,0.1648726,0.0005809259,0.0002173877,0.002950149,0.007686904,0.02477365,0.05204928,0.01498671,0.7308642,0.0002697455],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"dataset","genre_gemma":"empirical","genre_scores_codex":[0.4040211,0.001857381,0.03937415,0.0009520751,0.0007047731,0.000526417,0.5154803,0.01370722,0.02337658],"genre_scores_gemma":[0.2443833,0.0004830428,0.05409083,0.0003719759,0.00008516136,0.001012886,0.6921597,0.001102075,0.006311089],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.008877113,"threshold_uncertainty_score":0.02969694,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02820120575407398,"score_gpt":0.2577490291580065,"score_spread":0.2295478234039325,"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."}}