{"id":"W3134519208","doi":"10.33011/computel.v1i.949","title":"Expanding the JHU Bible Corpus for Machine Translation of the Indigenous Languages of North America","year":2021,"lang":"en","type":"article","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Indigenous; Machine translation; Variety (cybernetics); Translation (biology); Computer science; Linguistics; Natural language processing; Artificial intelligence; Resource (disambiguation); Philosophy; Biology","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":[0.001335026,0.0005898153,0.000677224,0.002990393,0.002732792,0.001218939,0.0007191508,0.0004676968,0.01324857],"category_scores_gemma":[0.006009198,0.0003419867,0.0003050443,0.003627894,0.0009103362,0.001175069,0.002527128,0.001164549,0.004056328],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00107628,"about_ca_system_score_gemma":0.003063517,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.03060237,"about_ca_topic_score_gemma":0.06995197,"domain_scores_codex":[0.9987878,0.0003866819,0.0001033077,0.0002589534,0.0003581001,0.0001050917],"domain_scores_gemma":[0.9966537,0.0009896239,0.0001351956,0.0007195745,0.001242965,0.0002589151],"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":[0.0008556825,0.000659312,0.02637507,0.002188007,0.0001874239,0.002138295,0.01313456,0.005462439,0.06975743,0.009577246,0.2004259,0.6692386],"study_design_scores_gemma":[0.000423484,0.0002882507,0.2067997,0.0004237651,0.0002232577,0.002575373,0.00705532,0.02539401,0.04209718,0.006382156,0.7081166,0.0002209723],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7890993,0.004293704,0.0397464,0.002272792,0.001489706,0.0009140512,0.07812221,0.00487654,0.07918538],"genre_scores_gemma":[0.6689849,0.001533744,0.09436734,0.0007325266,0.0005352989,0.001494694,0.2050132,0.001723639,0.0256146],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.03060237,"threshold_uncertainty_score":0.06084847,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01457573938741883,"score_gpt":0.2807156485594098,"score_spread":0.266139909171991,"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."}}