{"id":"W6891724053","doi":"10.48448/7w2v-mh92","title":"Revitalization of Indigenous Languages through Pre-processing and Neural Machine Translation: The case of Inuktitut","year":2020,"lang":"en","type":"other","venue":"Underline Science Inc.","topic":"","field":"","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université du Québec à Montréal","funders":"","keywords":"Indigenous; Context (archaeology); Focus (optics); Preprocessor; Task (project management); Machine translation; Indigenous language","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true,"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":[0.0003503977,0.000553963,0.0002705862,0.0006979703,0.001740569,0.001392661,0.0006297178,0.0004828203,0.003475723],"category_scores_gemma":[0.001141451,0.0001059205,0.0003095109,0.001146217,0.0007366601,0.0009648224,0.001012017,0.0007957921,0.001163666],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002234792,"about_ca_system_score_gemma":0.005489408,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.3431474,"about_ca_topic_score_gemma":0.4989911,"domain_scores_codex":[0.9997148,0.00006911388,0.00002039494,0.0000697502,0.00005577122,0.00007015762],"domain_scores_gemma":[0.9996116,0.00009843147,0.00003325347,0.00006053162,0.0001720046,0.00002435592],"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":[0.0003808498,0.0001873681,0.01103703,0.001387387,0.0001077659,0.003323927,0.008029262,0.01810207,0.06649752,0.02193559,0.01458185,0.8544294],"study_design_scores_gemma":[0.0001244842,0.0004704973,0.07643577,0.0008695821,0.0005903736,0.005464562,0.04249918,0.2750362,0.2065032,0.02789347,0.3637213,0.0003913447],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7751973,0.004943727,0.1292219,0.00306765,0.0004224748,0.0003842105,0.002145633,0.003416172,0.08120093],"genre_scores_gemma":[0.8574926,0.001752197,0.1121605,0.0004272955,0.0000447551,0.00008744132,0.003217179,0.0005369358,0.02428123],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6568526,"threshold_uncertainty_score":0.6823001,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03089203703095237,"score_gpt":0.3314773656303987,"score_spread":0.3005853285994463,"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."}}