{"id":"W6891826570","doi":"10.48448/2ahj-zr25","title":"SIDLR: Slot and Intent Detection Models for Low-Resource Language Varieties","year":2023,"lang":"en","type":"other","venue":"Underline Science Inc.","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Natural language; Variety (cybernetics); Feature (linguistics); Key (lock); Field (mathematics)","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":[0.002166119,0.002010638,0.001307716,0.002272338,0.001025853,0.003455459,0.003643393,0.001849752,0.02100023],"category_scores_gemma":[0.007824828,0.0009936814,0.002244571,0.001754889,0.0009046748,0.006257926,0.003267524,0.003181479,0.01546362],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001211997,"about_ca_system_score_gemma":0.001583283,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008695447,"about_ca_topic_score_gemma":0.01103783,"domain_scores_codex":[0.9982246,0.0003464373,0.0001220069,0.0006559555,0.0005060674,0.0001449914],"domain_scores_gemma":[0.9966617,0.001400715,0.000157271,0.0009875982,0.000671148,0.00012156],"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":[0.001081803,0.0005067284,0.006442792,0.0008701681,0.0002607553,0.000499493,0.000548753,0.04110987,0.01847057,0.04920746,0.2176338,0.6633678],"study_design_scores_gemma":[0.00007712679,0.0001344069,0.001128364,0.00008154062,0.00007488156,0.0003670289,0.0002134498,0.8496053,0.01629471,0.09060289,0.04132426,0.00009604527],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01190891,0.0005695468,0.8641341,0.0006368553,0.0003188203,0.0002293323,0.01167135,0.104121,0.006410045],"genre_scores_gemma":[0.2078542,0.0005440686,0.7179478,0.0007542847,0.0002769124,0.0004648252,0.04490901,0.008718828,0.01853001],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.02100023,"threshold_uncertainty_score":0.07025278,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01568839396889587,"score_gpt":0.2761772319823774,"score_spread":0.2604888380134815,"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."}}