{"id":"W3029712483","doi":"","title":"Evaluating the Impact of Sub-word Information and Cross-lingual Word Embeddings on Mi’kmaq Language Modelling","year":2020,"lang":"en","type":"article","venue":"Language Resources and Evaluation","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of New Brunswick","funders":"","keywords":"Word (group theory); Computer science; Language model; Natural language processing; Artificial intelligence; Indigenous language; Linguistics; Indigenous","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001556679,0.0001690499,0.0001757796,0.0001005336,0.0001921746,0.0004322769,0.000339213,0.00008413292,0.00001460959],"category_scores_gemma":[0.0005190167,0.0001135303,0.00006366464,0.0003424294,0.00006589433,0.0007218797,0.000181079,0.0002257398,0.000002940173],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004029844,"about_ca_system_score_gemma":0.00005344848,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003167629,"about_ca_topic_score_gemma":0.000005898708,"domain_scores_codex":[0.9984102,0.0001643522,0.000333596,0.0002617705,0.0006273326,0.0002027601],"domain_scores_gemma":[0.9989769,0.000200279,0.0003063382,0.0002592179,0.0001787126,0.00007849462],"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":[0.0001417316,0.00001710585,0.0004312525,0.0001154059,0.00003485965,0.000003390391,0.14527,0.03314385,0.01146598,0.0003071575,0.00006239786,0.8090069],"study_design_scores_gemma":[0.0004286174,0.0003130465,0.0007855647,0.00009550332,0.00002452375,0.000009737882,0.001250835,0.9856439,0.01040249,0.0008774888,0.00001226977,0.0001560145],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9738932,0.004756496,0.02041459,0.0002913648,0.00002415325,0.0003308461,0.000006075336,0.0001417455,0.0001414997],"genre_scores_gemma":[0.9816262,0.00003115524,0.01795025,0.0002443197,0.00009966587,0.00001502317,0.00001552051,0.000009905179,0.000007924223],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9525,"threshold_uncertainty_score":0.462963,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04360119139160799,"score_gpt":0.3828779568686983,"score_spread":0.3392767654770903,"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."}}