{"id":"W6966821068","doi":"10.48448/c9zh-0q23","title":"Toucan: Many-to-Many Translation for 150 African Language Pairs","year":2024,"lang":"en","type":"other","venue":"Underline Science Inc.","topic":"","field":"","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Machine translation; Translation (biology); Focus (optics); Field (mathematics); Natural language; Universal Networking Language; Machine translation software usability; Example-based machine translation","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":[0.00202601,0.001742603,0.000779362,0.001722088,0.001331343,0.00116734,0.001378797,0.001406596,0.01556582],"category_scores_gemma":[0.006359703,0.0004072655,0.0009116707,0.002105651,0.0004609894,0.002204581,0.001995916,0.001224887,0.008425481],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009688229,"about_ca_system_score_gemma":0.002016743,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009259207,"about_ca_topic_score_gemma":0.01695974,"domain_scores_codex":[0.9988468,0.0005153509,0.00007794084,0.0003033917,0.0001551171,0.0001013663],"domain_scores_gemma":[0.9987992,0.0005413796,0.00005902853,0.0002882892,0.0002484665,0.00006355646],"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":[0.001117824,0.0006135493,0.01230279,0.00129231,0.0003874314,0.001096038,0.0007614553,0.1318638,0.01047969,0.01157364,0.2538265,0.5746849],"study_design_scores_gemma":[0.0004782042,0.0005259564,0.00616571,0.0001756477,0.0001494863,0.000832082,0.00083904,0.8446018,0.02158959,0.01994514,0.1045718,0.0001256479],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5464813,0.004619198,0.2227956,0.004743182,0.002437268,0.001126441,0.07780979,0.07635703,0.06363018],"genre_scores_gemma":[0.6094724,0.0009558171,0.2242677,0.0008090077,0.0001925745,0.0009605992,0.1402473,0.003417783,0.01967683],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01556582,"threshold_uncertainty_score":0.05207282,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03308395462418463,"score_gpt":0.3263170054068772,"score_spread":0.2932330507826926,"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."}}