{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004681708,0.0002310482,0.0002321544,0.0002263133,0.0004270802,0.000127223,0.001221824,0.00006709129,0.00004601523],"category_scores_gemma":[0.0002300439,0.0002138642,0.0001340618,0.0004808106,0.00003141618,0.0002775677,0.0004523243,0.0004600352,0.000003300044],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001890662,"about_ca_system_score_gemma":0.0002563479,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007345293,"about_ca_topic_score_gemma":0.00003133346,"domain_scores_codex":[0.998176,0.0001292926,0.00021824,0.0005967395,0.0004311951,0.0004485064],"domain_scores_gemma":[0.9989184,0.0002459602,0.000156388,0.0004655011,0.0001159386,0.00009783555],"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":[0.001230912,0.002765073,0.0002286299,0.0006730879,0.0004442397,0.0006292502,0.2845955,0.1216926,0.1002904,0.07865702,0.00920717,0.3995861],"study_design_scores_gemma":[0.0005966155,0.0002593858,0.000004714106,0.000006044143,0.00001225716,0.000009440001,0.001801681,0.9620745,0.03287104,0.001504257,0.0005484751,0.0003116042],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.009911987,0.0005866728,0.9829593,0.0007742156,0.00007282117,0.0007109144,0.00004938469,0.003902163,0.001032589],"genre_scores_gemma":[0.5735071,3.694448e-7,0.4243146,0.0004279017,0.00002769897,0.0002639093,0.00002855764,0.00002218457,0.001407613],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8403819,"threshold_uncertainty_score":0.8721128,"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."}}