{"id":"W4385571737","doi":"10.18653/v1/2023.acl-long.609","title":"MasakhaPOS: Part-of-Speech Tagging for Typologically Diverse African languages","year":2023,"lang":"en","type":"article","venue":"","topic":"Language, Linguistics, Cultural Analysis","field":"Arts and Humanities","cited_by":13,"is_retracted":false,"has_abstract":true,"ca_institutions":"Mila - Quebec Artificial Intelligence Institute","funders":"DeepMind; International Development Research Centre; Rockefeller Foundation","keywords":"Blessing; Art history; Art; Theology; Philosophy","routes":{"ca_aff":true,"ca_fund":true,"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":[0.001364851,0.0006896934,0.000352817,0.00332156,0.001579853,0.001753446,0.0004909528,0.0005989979,0.009275363],"category_scores_gemma":[0.002452155,0.0005304961,0.0006138898,0.00235191,0.0004435737,0.002496026,0.002443511,0.0007321959,0.005698252],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004724167,"about_ca_system_score_gemma":0.001118687,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005150929,"about_ca_topic_score_gemma":0.01093849,"domain_scores_codex":[0.999366,0.0001743151,0.00007910702,0.0002114431,0.00009016531,0.00007894423],"domain_scores_gemma":[0.9986852,0.0005378674,0.0001888728,0.0002200971,0.0002395044,0.0001285471],"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":[0.001954643,0.0002420655,0.06292274,0.002439617,0.0002364057,0.003533097,0.01873687,0.002782759,0.160892,0.016388,0.148362,0.5815099],"study_design_scores_gemma":[0.0002035231,0.0002232849,0.1454693,0.001036088,0.0002795088,0.00281869,0.029393,0.03283559,0.05537516,0.02171129,0.710386,0.0002684523],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.4691932,0.005264939,0.2826973,0.001713657,0.001578184,0.001065791,0.1388303,0.03971102,0.05994563],"genre_scores_gemma":[0.5494871,0.00217238,0.2417194,0.0004824894,0.0002084547,0.001593498,0.1786487,0.006488391,0.01919963],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.009275363,"threshold_uncertainty_score":0.03102922,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07104347917596684,"score_gpt":0.2873835767518403,"score_spread":0.2163400975758735,"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."}}