{"id":"W6891700532","doi":"10.48448/fjkm-b086","title":"AfroLM: A Self-Active Learning-based Multilingual Pretrained Language Model for 23 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":"Language model; Context (archaeology); Code (set theory); Training set; Natural language; Language identification; Downstream (manufacturing); Code-switching","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":[0.001168249,0.002744231,0.0009978309,0.001191528,0.0008139353,0.001259315,0.002952015,0.001397745,0.008861269],"category_scores_gemma":[0.002824547,0.0007390029,0.002139531,0.00103991,0.0006676854,0.002641505,0.002059647,0.003355523,0.00641087],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001027251,"about_ca_system_score_gemma":0.001613012,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01857165,"about_ca_topic_score_gemma":0.0281921,"domain_scores_codex":[0.999332,0.0001847208,0.00004939169,0.0002395248,0.0001046261,0.00008965781],"domain_scores_gemma":[0.9992791,0.0003129993,0.0000430243,0.0001333156,0.0001790402,0.00005252408],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.001084559,0.0007920357,0.006963939,0.0009112455,0.0005399772,0.001128334,0.0007634606,0.1651116,0.01903998,0.005045002,0.1266293,0.6719906],"study_design_scores_gemma":[0.0001485111,0.000329855,0.002580467,0.0001196578,0.0001211514,0.0005553908,0.000391638,0.9263456,0.02114772,0.005731894,0.04237197,0.0001561544],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"other","genre_scores_codex":[0.2369379,0.006084448,0.5833277,0.002615204,0.002612032,0.00110805,0.04525437,0.09821998,0.02384043],"genre_scores_gemma":[0.4848293,0.001458603,0.3491827,0.001459029,0.000257946,0.001431595,0.1306751,0.003215549,0.02749018],"genre_candidate":"other","genre_consensus":null,"teacher_disagreement_score":0.01857165,"threshold_uncertainty_score":0.0369271,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02007904407409088,"score_gpt":0.3213358809207112,"score_spread":0.3012568368466204,"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."}}