{"id":"W4385570419","doi":"10.18653/v1/2023.americasnlp-1.10","title":"Towards the First Named Entity Recognition of Inuktitut for an Improved Machine Translation","year":2023,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université du Québec à Montréal","funders":"","keywords":"Computer science; Recall; Natural language processing; Artificial intelligence; Machine translation; Translation (biology); Indigenous; Named-entity recognition; Precision and recall; Word (group theory); Natural language; Speech recognition; Linguistics; Engineering","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":[0.0008568509,0.001172893,0.0008120404,0.001787444,0.001481446,0.002197707,0.001037619,0.0008267983,0.004047985],"category_scores_gemma":[0.002287761,0.0003727981,0.001136087,0.002206414,0.0004624519,0.003237966,0.001535937,0.001316405,0.00537794],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001655815,"about_ca_system_score_gemma":0.003896804,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.1009105,"about_ca_topic_score_gemma":0.1267242,"domain_scores_codex":[0.9991822,0.0002243653,0.00005771813,0.0003047023,0.000123757,0.0001071923],"domain_scores_gemma":[0.9987653,0.000197464,0.00006417726,0.0002769251,0.0006404129,0.00005565984],"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":[0.0003794522,0.000280541,0.01267937,0.0009396207,0.0003016467,0.001273733,0.002227105,0.04153939,0.06241446,0.03403263,0.05951445,0.7844177],"study_design_scores_gemma":[0.00003948422,0.0001290498,0.01149681,0.0001856853,0.0003693594,0.001124306,0.00174926,0.7590026,0.08164067,0.01794311,0.1261287,0.0001908984],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1113828,0.002951832,0.8445387,0.001440497,0.0007291324,0.0003408401,0.005481646,0.01467927,0.01845522],"genre_scores_gemma":[0.470958,0.001738419,0.4767534,0.0004190233,0.0001449695,0.0002301884,0.02764266,0.001676881,0.02043658],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.1009105,"threshold_uncertainty_score":0.2006463,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0940507350730992,"score_gpt":0.2888757707829049,"score_spread":0.1948250357098057,"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."}}