{"id":"W6910408253","doi":"10.48448/cdy6-9y18","title":"Machine Translation Through Cultural Texts: Can Verses and Prose Help Low-Resource Indigenous Models?","year":2024,"lang":"en","type":"other","venue":"Underline Science Inc.","topic":"","field":"","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Indigenous; Context (archaeology); Machine translation; Poetry; Indigenous culture; Indigenous language","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"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":[0.001410622,0.0007522653,0.0004126256,0.0009937572,0.001128125,0.00342854,0.0008821519,0.0006896293,0.005000918],"category_scores_gemma":[0.007346911,0.0002504397,0.0002888547,0.001247253,0.0009842991,0.004062807,0.0009456136,0.001155621,0.002617073],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001523456,"about_ca_system_score_gemma":0.002348855,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0721622,"about_ca_topic_score_gemma":0.141937,"domain_scores_codex":[0.9993476,0.0003851867,0.00002676361,0.0001323867,0.00006133154,0.00004662717],"domain_scores_gemma":[0.9978768,0.001232198,0.0001159451,0.0002950366,0.0003850528,0.00009494067],"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":[0.0002873032,0.0002093824,0.02868451,0.0004348674,0.0001666217,0.0004358265,0.007708841,0.05010153,0.009463869,0.04918728,0.01307055,0.8402495],"study_design_scores_gemma":[0.00005338817,0.000136762,0.01654705,0.0003934506,0.0001622782,0.0003575459,0.00901881,0.7746924,0.01518527,0.1006495,0.08266947,0.0001340871],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.4804329,0.005518705,0.359669,0.01552768,0.0004082372,0.000261102,0.003353572,0.00624973,0.1285791],"genre_scores_gemma":[0.8975098,0.0009693294,0.08846733,0.0002953753,0.00006844799,0.00005127534,0.00201207,0.0003288393,0.01029755],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.0721622,"threshold_uncertainty_score":0.1434844,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03701990535880565,"score_gpt":0.302053278962979,"score_spread":0.2650333736041733,"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."}}