{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001137738,0.001291741,0.0004745271,0.003450082,0.001260135,0.001055284,0.0009226864,0.0007959707,0.01605863],"category_scores_gemma":[0.002885159,0.0004108934,0.0006229645,0.002460184,0.0004631341,0.002464046,0.003141271,0.001001902,0.01434045],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005321294,"about_ca_system_score_gemma":0.001200495,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007226986,"about_ca_topic_score_gemma":0.01496411,"domain_scores_codex":[0.9992205,0.0001670538,0.00008159249,0.0002775974,0.0001401467,0.0001131035],"domain_scores_gemma":[0.9989139,0.0003173436,0.0001253953,0.0003074454,0.0001909656,0.0001449332],"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":[0.001731271,0.0002777477,0.03808631,0.00281555,0.0001779113,0.001457341,0.002914098,0.002863602,0.03462842,0.007208271,0.693984,0.2138556],"study_design_scores_gemma":[0.0002464441,0.0001371125,0.05348896,0.0004539729,0.00008983058,0.001323388,0.003019944,0.01017762,0.02262259,0.007945702,0.9003455,0.0001489544],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"dataset","genre_gemma":"empirical","genre_scores_codex":[0.1077294,0.001360623,0.02706909,0.0007683026,0.0008104773,0.0003715444,0.8124969,0.02071458,0.02867914],"genre_scores_gemma":[0.06682105,0.000330857,0.03205607,0.0003006274,0.00007628737,0.0006468519,0.8925962,0.001591571,0.0055805],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01605863,"threshold_uncertainty_score":0.05372143,"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."}}