{"id":"W6891668889","doi":"10.48448/6gcx-2y73","title":"Unsupervised Morphological Segmentation with Adaptor Grammars for Inuit Language Family: an Empirical Study of Inuinnaqtun","year":2021,"lang":"en","type":"other","venue":"Underline Science Inc.","topic":"","field":"","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université du Québec à Montréal","funders":"","keywords":"Rule-based machine translation; Segmentation; Empirical research; Text segmentation; Constructed language; Natural language","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":[0.001511822,0.0006351005,0.00041411,0.001553881,0.001955191,0.001331764,0.001248399,0.0005504004,0.003451351],"category_scores_gemma":[0.007254064,0.0003064239,0.000433585,0.001964311,0.001420083,0.001628003,0.001181663,0.0008414155,0.0009089087],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002068302,"about_ca_system_score_gemma":0.001617829,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.1428417,"about_ca_topic_score_gemma":0.2254123,"domain_scores_codex":[0.9985967,0.0005796272,0.00009356929,0.0003525319,0.0002384738,0.0001390508],"domain_scores_gemma":[0.9935961,0.003567214,0.0004630701,0.0008152829,0.001139598,0.0004187613],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.001777696,0.001806699,0.5205916,0.001858373,0.0004911048,0.0130775,0.09216656,0.01033154,0.03721669,0.009284301,0.02261837,0.2887795],"study_design_scores_gemma":[0.0001093268,0.0006467599,0.762776,0.0002687307,0.0003223379,0.008781037,0.07858452,0.07216364,0.01691192,0.002913769,0.05629514,0.0002268958],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9943464,0.0001540135,0.001673965,0.00005171555,0.000007912826,0.00004530395,0.0008010988,0.0001418709,0.002777661],"genre_scores_gemma":[0.9904551,0.00008498286,0.004052784,0.00003505718,0.000003812109,0.00004620288,0.003659538,0.0001458637,0.001516717],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8571583,"threshold_uncertainty_score":0.2840205,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06292921244897032,"score_gpt":0.3710408988100257,"score_spread":0.3081116863610554,"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."}}