{"id":"W6910603797","doi":"10.48448/zsws-za13","title":"MasakhaPOS: Part-of-Speech Tagging for Typologically Diverse African languages","year":2022,"lang":"en","type":"other","venue":"Underline Science Inc.","topic":"","field":"","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University; Mila - Quebec Artificial Intelligence Institute","funders":"","keywords":"Conditional random field; Transfer (computing); Baseline (sea); Field (mathematics); Training set; Transfer of learning; Language family","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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00166894,0.0004157159,0.0005731023,0.001234201,0.0004013398,0.00008406258,0.001979332,0.0001776931,0.02028117],"category_scores_gemma":[0.0008507389,0.000362617,0.0001527098,0.001764523,0.002182901,0.0001365286,0.0008803345,0.0003565209,0.0004996754],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003688886,"about_ca_system_score_gemma":0.0006025415,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004481555,"about_ca_topic_score_gemma":0.0005771465,"domain_scores_codex":[0.9962816,0.00009591183,0.0004218156,0.001050667,0.001268324,0.0008816893],"domain_scores_gemma":[0.9977999,0.0002205841,0.000714094,0.0008847736,0.0001704127,0.0002101748],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00008950606,0.0003674421,0.0006320396,0.000177824,0.0001321732,0.0001102658,0.0006253214,0.0001290215,0.008484205,0.03023368,0.9185669,0.04045159],"study_design_scores_gemma":[0.0004891779,0.0002854073,0.00003194217,0.00006660428,0.00008140814,0.00001375552,0.003868828,0.0007312255,0.0003613768,0.000483379,0.9930521,0.000534793],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"other","genre_gemma":"other","genre_scores_codex":[0.0004664187,0.000749154,0.000607798,0.0005496022,0.001008651,0.001679355,0.003225891,0.001091682,0.9906214],"genre_scores_gemma":[0.04859347,0.0001535191,0.1490221,0.001055567,0.002211905,0.0004492168,0.001101599,0.002147276,0.7952654],"genre_candidate":"other","genre_consensus":"other","teacher_disagreement_score":0.1953561,"threshold_uncertainty_score":0.9998826,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04548040353838474,"score_gpt":0.3323804024692688,"score_spread":0.286899998930884,"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."}}