{"id":"W4402671031","doi":"10.18653/v1/2024.acl-long.691","title":"Cheetah: Natural Language Generation for 517 African Languages","year":2024,"lang":"en","type":"article","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Alliance de recherche numérique du Canada; State Government of Victoria; Social Sciences and Humanities Research Council of Canada; Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs","keywords":"Natural language generation; Computer science; Natural language; Linguistics; Natural language processing; Philosophy","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001134869,0.0006437346,0.0003474796,0.0007350981,0.0006663688,0.0008731143,0.001196337,0.0007658942,0.01294761],"category_scores_gemma":[0.003197299,0.0003167067,0.0006663488,0.0004578304,0.0005068103,0.002264783,0.001994615,0.00124158,0.002977813],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006559195,"about_ca_system_score_gemma":0.001219268,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004325008,"about_ca_topic_score_gemma":0.00914443,"domain_scores_codex":[0.9996173,0.0001526876,0.0000225378,0.0001050056,0.00006980961,0.00003258204],"domain_scores_gemma":[0.9990263,0.0005818435,0.00004106867,0.0001723928,0.0001311703,0.00004728079],"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":[0.001064686,0.0005226499,0.01011571,0.001456665,0.0002487502,0.001511501,0.002753179,0.08571617,0.03238642,0.04166129,0.1738036,0.6487594],"study_design_scores_gemma":[0.0002990792,0.0002813215,0.003191028,0.0001053607,0.00007979223,0.0008644848,0.0008001882,0.8003032,0.02625832,0.03020898,0.1375152,0.00009308873],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.2084263,0.001229319,0.6181015,0.003014843,0.0005633551,0.001940287,0.02147202,0.1123366,0.03291577],"genre_scores_gemma":[0.5241164,0.0003965316,0.4308632,0.0006713283,0.00005798485,0.0008120339,0.02751074,0.002681293,0.01289052],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01294761,"threshold_uncertainty_score":0.0433141,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0138762489736982,"score_gpt":0.3075812125610614,"score_spread":0.2937049635873631,"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."}}