{"id":"W4385571607","doi":"10.18653/v1/2023.findings-acl.97","title":"SERENGETI: Massively Multilingual Language Models for Africa","year":2023,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"Alliance de recherche numérique du Canada; Social Sciences and Humanities Research Council of Canada; Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs; Advanced Micro Devices","keywords":"Computer science; Set (abstract data type); Natural language processing; Task (project management); Artificial intelligence; Similarity (geometry); Language model; Natural language","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":[0.001225255,0.002362848,0.0006959978,0.001015569,0.0008604964,0.001290979,0.002033497,0.001018742,0.007719918],"category_scores_gemma":[0.003447008,0.0006746462,0.001801152,0.0007707955,0.0003705923,0.002963261,0.001901472,0.003373475,0.004479994],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009771205,"about_ca_system_score_gemma":0.001327599,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0184707,"about_ca_topic_score_gemma":0.03292036,"domain_scores_codex":[0.9995939,0.0001616924,0.0000168965,0.0001412842,0.00003166635,0.0000545396],"domain_scores_gemma":[0.9993407,0.0003486327,0.00003227162,0.0001103439,0.0001042638,0.00006378857],"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":[0.001296516,0.0006565425,0.01484315,0.0008856729,0.001128937,0.0009570884,0.001255177,0.2959116,0.00961355,0.01058781,0.3116099,0.3512539],"study_design_scores_gemma":[0.0002548755,0.0001940493,0.003154731,0.0001621427,0.000155105,0.0002631533,0.0003826517,0.9224406,0.004864667,0.01724206,0.05079419,0.00009163204],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3351111,0.008264231,0.437032,0.006717981,0.003753625,0.001073519,0.08138852,0.09563801,0.03102113],"genre_scores_gemma":[0.6727493,0.001637747,0.1835764,0.001569323,0.0005315384,0.001317969,0.115127,0.003919554,0.01957112],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.0184707,"threshold_uncertainty_score":0.03672642,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06771763747740082,"score_gpt":0.2975696648305111,"score_spread":0.2298520273531102,"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."}}