{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.001365828,0.0005359427,0.0004796745,0.002314041,0.0001667919,0.0003492955,0.001261458,0.0002516745,0.001418527],"category_scores_gemma":[0.0001775447,0.000489479,0.0001671214,0.002786485,0.0007221505,0.0002076685,0.0001360988,0.0003317315,0.01088295],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004633429,"about_ca_system_score_gemma":0.0006557842,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006503433,"about_ca_topic_score_gemma":0.003037003,"domain_scores_codex":[0.9958822,0.00004482598,0.000430322,0.001427574,0.001217192,0.0009979014],"domain_scores_gemma":[0.9982923,0.00008848849,0.0002113702,0.0008885671,0.0001187464,0.0004005168],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00004321044,0.0001331742,0.000007229754,0.0003443132,0.0000769959,0.00003671489,0.003960818,0.00009237332,0.01642733,0.01157652,0.9241629,0.04313837],"study_design_scores_gemma":[0.0004318459,0.0002053302,0.00001256766,0.0003772642,0.0001368496,0.00001075807,0.001678902,0.01453436,0.0006540748,0.001047908,0.9800918,0.0008183727],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"other","genre_gemma":"other","genre_scores_codex":[0.0001785434,0.002172702,0.03238216,0.002271387,0.002333863,0.00359514,0.002883303,0.00262724,0.9515557],"genre_scores_gemma":[0.06018338,0.00001334358,0.06663355,0.0006008316,0.002020899,0.0003471156,0.0003436819,0.002663315,0.8671939],"genre_candidate":"other","genre_consensus":"other","teacher_disagreement_score":0.08436177,"threshold_uncertainty_score":0.9997557,"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."}}