{"id":"W4385574228","doi":"10.18653/v1/2022.sustainlp-1.11","title":"AfroLM: A Self-Active Learning-based Multilingual Pretrained Language Model for 23 African Languages","year":2022,"lang":"en","type":"article","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":25,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University; Mila - Quebec Artificial Intelligence Institute","funders":"","keywords":"Computer science; Natural language processing; Simple (philosophy); Artificial intelligence; Natural language; Linguistics; Programming language; Philosophy","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":[0.0009547158,0.001199393,0.000697797,0.0007901788,0.0006587549,0.0009562652,0.00203979,0.0009573847,0.00454398],"category_scores_gemma":[0.001375324,0.0005274671,0.001182308,0.0003795825,0.00027599,0.002421601,0.001668162,0.002330663,0.002666682],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007253748,"about_ca_system_score_gemma":0.001092345,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01142695,"about_ca_topic_score_gemma":0.02088928,"domain_scores_codex":[0.9996663,0.000091734,0.00002268256,0.000131598,0.00003980381,0.00004785548],"domain_scores_gemma":[0.999575,0.0002214422,0.00001867331,0.0000473715,0.00009889313,0.00003856811],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.001015173,0.0005705645,0.003756777,0.0002379864,0.0003616164,0.0003069454,0.0003331876,0.1211578,0.01304939,0.00314945,0.02290647,0.8331548],"study_design_scores_gemma":[0.00006608034,0.0001588693,0.0006577801,0.00003351303,0.00007767537,0.00009923089,0.0001308318,0.9800369,0.008256203,0.003324626,0.007130449,0.00002797642],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1651993,0.002714772,0.7840517,0.0009156737,0.0005288749,0.0003149856,0.004424274,0.034461,0.007389341],"genre_scores_gemma":[0.64498,0.0007928271,0.3183356,0.0007015596,0.0001376187,0.0005884704,0.01559938,0.001862756,0.01700185],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01142695,"threshold_uncertainty_score":0.02272087,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01259568714359499,"score_gpt":0.2895668403321396,"score_spread":0.2769711531885446,"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."}}