{"id":"W3116587780","doi":"10.18653/v1/2020.coling-main.410","title":"Revitalization of Indigenous Languages through Pre-processing and Neural Machine Translation: The case of Inuktitut","year":2020,"lang":"en","type":"article","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":19,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université du Québec à Montréal","funders":"","keywords":"Machine translation; Computer science; Artificial intelligence; Natural language processing; Indigenous; Preprocessor; Context (archaeology); Focus (optics); Linguistics; History","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":[0.0003537182,0.0005432495,0.0003124865,0.0007306436,0.002067668,0.001373871,0.0006234014,0.0004845273,0.002528012],"category_scores_gemma":[0.001201755,0.0001226013,0.0003261427,0.001295971,0.0008408802,0.0009907958,0.0009561113,0.0009135951,0.0006815516],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002637386,"about_ca_system_score_gemma":0.006011603,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.3859372,"about_ca_topic_score_gemma":0.5559869,"domain_scores_codex":[0.9997193,0.00006120731,0.00002003038,0.00006770156,0.00005832956,0.00007350575],"domain_scores_gemma":[0.9995907,0.0001136958,0.00003282315,0.00005621093,0.000183047,0.00002361621],"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":[0.0003945965,0.0002130006,0.0130285,0.001725711,0.0001165409,0.005407504,0.01396228,0.02144997,0.08873742,0.03388062,0.01286882,0.8082151],"study_design_scores_gemma":[0.0001283763,0.0004585277,0.08552148,0.0008371742,0.0005743869,0.007415527,0.05915954,0.2522782,0.2151516,0.03008155,0.3479767,0.0004168441],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.8017094,0.004022399,0.1282243,0.002467914,0.0003217927,0.0003873145,0.001588038,0.002083198,0.0591957],"genre_scores_gemma":[0.8619947,0.00166222,0.1161369,0.0003548913,0.00003562897,0.00008574237,0.002293558,0.0003720872,0.01706417],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.3859372,"threshold_uncertainty_score":0.7673816,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0221484901184939,"score_gpt":0.2994031450251255,"score_spread":0.2772546549066316,"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."}}