{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001897632,0.00008273435,0.00009279274,0.00008520745,0.00006735183,0.00006825282,0.0005366658,0.00004302924,0.000009336739],"category_scores_gemma":[0.00004427473,0.00007205505,0.00005426287,0.0002246879,0.000008079551,0.0002370872,0.0002102038,0.00005236006,0.00008429819],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001514475,"about_ca_system_score_gemma":0.00003743774,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002287861,"about_ca_topic_score_gemma":0.00000906588,"domain_scores_codex":[0.9991144,0.00001384905,0.0001301144,0.0003075565,0.0001500698,0.0002839894],"domain_scores_gemma":[0.9993783,0.0001190639,0.00002538758,0.0003675251,0.00004896085,0.00006074722],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001230938,0.0000692159,0.00003618668,0.0000821168,0.00004361348,0.00007033609,0.0334501,0.09770781,0.005730478,0.4973618,0.01594078,0.3494952],"study_design_scores_gemma":[0.0002039529,0.00001525661,0.00001547146,0.000004369261,0.000001571655,0.00000111967,0.0002964063,0.982585,0.001843328,0.01308276,0.001850572,0.0001002356],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01500154,0.00003880518,0.9728177,0.0007337512,0.0002253362,0.0001676846,0.000004078435,0.0007683156,0.01024286],"genre_scores_gemma":[0.7568104,0.000002290215,0.23151,0.00008647716,0.00008064874,0.00003702989,0.000002394737,0.000009293852,0.01146149],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8848771,"threshold_uncertainty_score":0.2938319,"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."}}