{"id":"W3029985558","doi":"","title":"The Nunavut Hansard Inuktitut-English Parallel Corpus 3.0 with Preliminary Machine Translation Results.","year":2020,"lang":"en","type":"article","venue":"Language Resources and Evaluation","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":33,"is_retracted":false,"has_abstract":false,"ca_institutions":"","funders":"","keywords":"Computer science; Sentence; Machine translation; Indigenous; Natural language processing; Indigenous language; Linguistics; Artificial intelligence; Speech recognition","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008073307,0.0001427455,0.0001207498,0.00003648587,0.000286563,0.0003552744,0.0004124393,0.00006632825,0.000005408998],"category_scores_gemma":[0.0002382569,0.00008716647,0.00002882518,0.0002905898,0.00006623735,0.0003836568,0.0000803829,0.0001945013,0.000002548366],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002276674,"about_ca_system_score_gemma":0.00003549002,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006982894,"about_ca_topic_score_gemma":0.00008955626,"domain_scores_codex":[0.9985309,0.0001760907,0.0002179338,0.0003550021,0.0005361178,0.0001839269],"domain_scores_gemma":[0.999167,0.0001666737,0.000144884,0.0002946794,0.0001469289,0.00007983297],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0005256292,0.00001737937,0.0001342163,0.0000434204,0.00002388211,0.00001873686,0.0631484,0.0004281433,0.0005339294,0.0008345634,0.0003808679,0.9339108],"study_design_scores_gemma":[0.002177641,0.0009302179,0.001117739,0.0001254465,0.00008804892,0.00003299665,0.001576946,0.9750209,0.002289099,0.001760268,0.01445615,0.0004245375],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2267246,0.2083615,0.5281528,0.02646733,0.0002744236,0.002568065,0.00004174532,0.002247566,0.005161991],"genre_scores_gemma":[0.9268298,0.0001294545,0.07227834,0.0004378763,0.0001663515,0.00004248713,0.00003559269,0.00001327704,0.00006684927],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9745927,"threshold_uncertainty_score":0.3554545,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02149560907502406,"score_gpt":0.266804596939113,"score_spread":0.2453089878640889,"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."}}