{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003587221,0.002254556,0.001115364,0.001208242,0.0007369638,0.001730144,0.003018281,0.001796048,0.00648508],"category_scores_gemma":[0.00771651,0.0007944302,0.001813153,0.0007333995,0.0006207648,0.003875262,0.002715501,0.004270844,0.005119242],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001027461,"about_ca_system_score_gemma":0.001245098,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007443355,"about_ca_topic_score_gemma":0.01088338,"domain_scores_codex":[0.9985758,0.0005930502,0.00007706069,0.0004370505,0.0001947083,0.0001223609],"domain_scores_gemma":[0.9963526,0.002358221,0.0001257232,0.0005848808,0.0004285428,0.0001499916],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.001744198,0.0008667061,0.008283926,0.0007762575,0.0003954272,0.0005288005,0.001323209,0.153633,0.02456304,0.01578021,0.07165858,0.7204466],"study_design_scores_gemma":[0.00006194302,0.0001498142,0.0009237686,0.00002592147,0.00004494421,0.0001709134,0.0001328556,0.9744505,0.005855951,0.0115811,0.00654543,0.00005678007],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.09287474,0.001884136,0.8519716,0.001229658,0.0004750918,0.0003825938,0.005342419,0.04094058,0.004899228],"genre_scores_gemma":[0.5605634,0.0005801305,0.4080275,0.0008588745,0.0003167308,0.0007329314,0.01525455,0.002075996,0.01158979],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.007443355,"threshold_uncertainty_score":0.02169472,"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."}}