{"id":"W6976084273","doi":"10.60692/2crmm-aaz77","title":"AfroLM: A Self-Active Learning-based Multilingual Pretrained Language Model for 23 African Languages","year":2022,"lang":"en","type":"article","venue":"Greater South Information System","topic":"Nanotechnology research and applications","field":"Engineering","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; Language identification; Natural language; Code-switching; Downstream (manufacturing)","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":[0.001183303,0.002363267,0.0009622488,0.001110245,0.0007776453,0.001266747,0.002691207,0.001282929,0.007431809],"category_scores_gemma":[0.002748577,0.0007703878,0.001905782,0.0008686702,0.0006083443,0.002586537,0.002180875,0.003292006,0.005776548],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008703624,"about_ca_system_score_gemma":0.001528888,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01327395,"about_ca_topic_score_gemma":0.02270823,"domain_scores_codex":[0.9993916,0.0001552365,0.000044686,0.0002244339,0.0001017049,0.00008236212],"domain_scores_gemma":[0.999266,0.0003239351,0.00003977045,0.0001352044,0.0001843536,0.00005073729],"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":[0.0008249223,0.000726174,0.006409817,0.0007263229,0.0005196299,0.0008964555,0.0007257593,0.168666,0.02024046,0.004909701,0.08409529,0.7112595],"study_design_scores_gemma":[0.0001041989,0.0002453438,0.001726794,0.00008889399,0.0001071499,0.0003726329,0.0002679036,0.942171,0.01988188,0.00459881,0.03032755,0.0001077334],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1948081,0.004827042,0.6756724,0.001850265,0.001926819,0.0007926239,0.01960562,0.08205006,0.01846713],"genre_scores_gemma":[0.4726208,0.001446034,0.4193441,0.00137194,0.0002413722,0.001224119,0.07460514,0.003209545,0.02593704],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01327395,"threshold_uncertainty_score":0.02639335,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01695083142444189,"score_gpt":0.2339535317920627,"score_spread":0.2170027003676208,"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."}}