{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001256915,0.0005903795,0.0008556328,0.001087354,0.0001838626,0.0001592508,0.00123954,0.0002993213,0.0007446398],"category_scores_gemma":[0.0001947724,0.0004513095,0.00008455835,0.002328173,0.001324033,0.0002550797,0.0002712141,0.0003694888,0.00003927888],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004344469,"about_ca_system_score_gemma":0.001320041,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001321182,"about_ca_topic_score_gemma":0.01165887,"domain_scores_codex":[0.9949141,0.0002953251,0.0006272815,0.001564086,0.001850415,0.0007487533],"domain_scores_gemma":[0.9974241,0.0001273248,0.0005542003,0.001122561,0.0004271201,0.0003447215],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"qualitative","study_design_scores_codex":[0.002164329,0.03119885,0.04442686,0.0007984824,0.00107157,0.001400194,0.05912868,0.001399322,0.7387136,0.0006280001,0.07839404,0.04067606],"study_design_scores_gemma":[0.05661545,0.06590051,0.05860806,0.002382538,0.002916951,0.0004634126,0.7057672,0.06290869,0.01393699,0.0006845474,0.01842429,0.01139138],"study_design_candidate":"qualitative","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9886963,0.0002057762,0.002595493,0.00004353707,0.0002470464,0.003796342,0.001060775,0.0004478587,0.002906851],"genre_scores_gemma":[0.8999294,0.00000883364,0.08147405,0.0003300612,0.0003683885,0.0003730195,0.001139546,0.000916534,0.01546015],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7247766,"threshold_uncertainty_score":0.9997939,"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."}}