{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008722802,0.002061209,0.001074572,0.00245096,0.0009325017,0.00306363,0.001980967,0.001948529,0.004441273],"category_scores_gemma":[0.03581233,0.000618205,0.001314978,0.002233734,0.0008367283,0.007737929,0.002865872,0.00252665,0.002492253],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001418122,"about_ca_system_score_gemma":0.002024506,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.03672968,"about_ca_topic_score_gemma":0.03301183,"domain_scores_codex":[0.9920254,0.004814218,0.0006949856,0.001238303,0.0008478443,0.0003791706],"domain_scores_gemma":[0.9687409,0.02512864,0.0004387133,0.002328484,0.002747961,0.0006152811],"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":[0.00650753,0.002292757,0.03061942,0.001512379,0.001976655,0.0003973734,0.001064696,0.3347139,0.01257837,0.005013218,0.01389672,0.5894269],"study_design_scores_gemma":[0.0001170418,0.0005223123,0.004014648,0.00007887805,0.000344825,0.000112473,0.000700795,0.9779755,0.01048663,0.003023161,0.002549969,0.00007376164],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.8485186,0.003277872,0.1177187,0.001473098,0.0007099759,0.0003396554,0.005752017,0.0104263,0.01178386],"genre_scores_gemma":[0.9187188,0.0005444863,0.06586937,0.0001927002,0.00005477988,0.000130958,0.01122233,0.0005426561,0.002723952],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.03672968,"threshold_uncertainty_score":0.07303178,"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."}}