{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003264385,0.001492224,0.001309856,0.004440198,0.003944851,0.002618596,0.001898297,0.001098395,0.04886709],"category_scores_gemma":[0.01071048,0.0007707741,0.0005438368,0.004783424,0.0009296555,0.002248779,0.004059492,0.001328,0.02704414],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001799707,"about_ca_system_score_gemma":0.006332908,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.07243703,"about_ca_topic_score_gemma":0.0986783,"domain_scores_codex":[0.9966558,0.001575168,0.0002603417,0.0006720349,0.0005477293,0.0002888702],"domain_scores_gemma":[0.995404,0.001217031,0.0001329467,0.0007640434,0.002080471,0.0004015454],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00447803,0.001147192,0.006520201,0.005194644,0.000416802,0.002465921,0.005251723,0.004453098,0.03537055,0.01467373,0.6433319,0.2766962],"study_design_scores_gemma":[0.001820175,0.0006039712,0.03017794,0.00100806,0.0005303608,0.002277365,0.004137444,0.01249416,0.04527503,0.006427313,0.8949913,0.0002567512],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"dataset","genre_gemma":"empirical","genre_scores_codex":[0.2388603,0.01079709,0.04508836,0.003389696,0.002971737,0.003774299,0.4888813,0.0269908,0.1792465],"genre_scores_gemma":[0.1933154,0.001514824,0.08629465,0.0005749202,0.0002604269,0.002897145,0.6639236,0.006602052,0.04461699],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.07243703,"threshold_uncertainty_score":0.1634766,"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."}}