{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003996415,0.00004885654,0.00006502181,0.00004688127,0.00008025737,0.00003966641,0.0003027885,0.0000304093,0.00001077296],"category_scores_gemma":[0.00002803754,0.00003447749,0.00004289321,0.000198726,0.00001311386,0.0003275911,0.00003552246,0.00003777005,0.00000549703],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000009686478,"about_ca_system_score_gemma":0.00002644661,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003452313,"about_ca_topic_score_gemma":0.0009019136,"domain_scores_codex":[0.9994668,0.00001790059,0.000150799,0.0001606573,0.000101841,0.0001020271],"domain_scores_gemma":[0.9995725,0.00005058721,0.00004090521,0.0002568258,0.0000593402,0.00001990007],"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":[0.000009966151,0.00002664867,0.00008577584,0.0000391261,0.000009071774,1.420527e-7,0.001373518,0.0002485873,0.001810872,0.003621993,0.0001178643,0.9926564],"study_design_scores_gemma":[0.0002536825,0.00005370105,0.0006352662,0.000004879565,0.000004095381,4.920635e-7,0.00001826872,0.9846136,0.003455593,0.01000148,0.0009084578,0.00005051364],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03846311,0.00001419431,0.9577726,0.00226174,0.000224562,0.000315156,0.00000867682,0.0001544755,0.0007854455],"genre_scores_gemma":[0.9436717,0.000006304521,0.05600027,0.0001379952,0.00004405411,0.0000387732,0.00002058987,0.00000385605,0.00007644363],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9926059,"threshold_uncertainty_score":0.1405951,"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."}}