{"id":"W3147742655","doi":"10.48550/arxiv.2103.04225","title":"Translating the Unseen? Yoruba-English MT in Low-Resource, Morphologically-Unmarked Settings","year":2021,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Yoruba; Linguistics; Resource (disambiguation); Computer science; History; Artificial intelligence; Philosophy","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":[0.001263728,0.0008509467,0.00065151,0.000387947,0.000678983,0.00179068,0.0007276433,0.001067463,0.003871132],"category_scores_gemma":[0.008836833,0.0003510209,0.0003051237,0.0006075597,0.0005830473,0.002814474,0.001174323,0.0008406194,0.002347786],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009366683,"about_ca_system_score_gemma":0.0009291482,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01444267,"about_ca_topic_score_gemma":0.02449549,"domain_scores_codex":[0.9990283,0.0004838165,0.00005790407,0.0002733092,0.00009292148,0.00006375817],"domain_scores_gemma":[0.9976718,0.001323246,0.0001125492,0.000396806,0.0004340612,0.00006151384],"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":[0.001955652,0.0005486209,0.02044085,0.002176252,0.0003317508,0.004200136,0.006450245,0.186149,0.1648351,0.04701292,0.04339914,0.5225003],"study_design_scores_gemma":[0.000140367,0.0002621142,0.01059723,0.0002163285,0.000148949,0.001146327,0.00331292,0.8135267,0.07899545,0.05087069,0.04065459,0.0001283192],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7200677,0.001147856,0.2324219,0.002912594,0.0004700318,0.0001393316,0.003619324,0.01179215,0.02742888],"genre_scores_gemma":[0.9379498,0.0002129102,0.05410141,0.0002368358,0.00003615383,0.00005792676,0.002758398,0.0006650941,0.003981544],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01444267,"threshold_uncertainty_score":0.02871722,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03069907811360257,"score_gpt":0.1864195074878402,"score_spread":0.1557204293742376,"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."}}