{"id":"W4386576671","doi":"10.18653/v1/2023.vardial-1.24","title":"SIDLR: Slot and Intent Detection Models for Low-Resource Language Varieties","year":2023,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; Margin (machine learning); Task (project management); Dialog box; Generalization; Baseline (sea); Encoder; Natural language; Language model; Natural language understanding; Natural language processing; Resource (disambiguation); Artificial intelligence; Speech recognition; Machine learning; Engineering; World Wide Web","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":[0.000177664,0.00006127507,0.0000672524,0.00006945305,0.00007311472,0.00009019279,0.0001853361,0.00003250886,0.00000229614],"category_scores_gemma":[0.0000230068,0.00005310106,0.00002586117,0.0001242608,0.00001167294,0.0001992099,0.0001833265,0.00004250383,0.000009170729],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001362441,"about_ca_system_score_gemma":0.000008952023,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000622769,"about_ca_topic_score_gemma":0.00003733606,"domain_scores_codex":[0.9994164,0.00001180005,0.0000964987,0.0002209888,0.00009866787,0.0001556116],"domain_scores_gemma":[0.9996319,0.00006725787,0.0000182636,0.0002194556,0.00002463929,0.00003849489],"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":[0.00002096855,0.00003206514,0.00002895785,0.0001387387,0.00003372231,0.00001028784,0.01547373,0.06181294,0.0182389,0.3203043,0.001297178,0.5826082],"study_design_scores_gemma":[0.0001227677,0.00002684326,0.00002433772,0.000005039751,0.00000174425,0.000003058204,0.0003640096,0.9785536,0.006289053,0.01404426,0.0004962191,0.00006905307],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06431516,0.0000355028,0.9332443,0.0005283687,0.0001152699,0.0001216217,6.308221e-7,0.0003881416,0.001250994],"genre_scores_gemma":[0.9800877,0.000003841534,0.01705866,0.0002369782,0.00004776537,0.00002769184,9.768355e-7,0.000006175586,0.002530225],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9167407,"threshold_uncertainty_score":0.2165398,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02546577722256097,"score_gpt":0.239637146382223,"score_spread":0.214171369159662,"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."}}