{"id":"W4392910835","doi":"10.1109/icassp48485.2024.10446325","title":"A Birgat Model for Multi-Intent Spoken Language Understanding with Hierarchical Semantic Frames","year":2024,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Optech (Canada)","funders":"National Natural Science Foundation of China","keywords":"Computer science; Utterance; Natural language processing; Artificial intelligence; Pointer (user interface); Spoken language; Generalizability theory; Graph; Margin (machine learning); Machine learning; Theoretical computer science","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":[0.001009289,0.0007846689,0.0006712375,0.000837352,0.0005129566,0.001268836,0.002150793,0.001559979,0.004681018],"category_scores_gemma":[0.002851659,0.0005082326,0.0009018896,0.0008074062,0.0006695109,0.003085695,0.001424168,0.002614702,0.001902557],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001548451,"about_ca_system_score_gemma":0.001387316,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01319145,"about_ca_topic_score_gemma":0.02633064,"domain_scores_codex":[0.9995769,0.0001203782,0.00002002477,0.0001616669,0.00006715033,0.00005388672],"domain_scores_gemma":[0.9992256,0.0004403515,0.00005028841,0.0001097491,0.0001252673,0.00004869297],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0005442405,0.0002886692,0.002817914,0.0002493967,0.0001178436,0.000323685,0.001389072,0.5081102,0.01020293,0.1813362,0.01376242,0.2808575],"study_design_scores_gemma":[0.000008733648,0.00001999245,0.0001139912,0.000009762034,0.00001046775,0.00001997035,0.00003099644,0.9625196,0.0005408692,0.03536664,0.001351404,0.000007501397],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02467704,0.0004030176,0.967176,0.0006455933,0.00007750899,0.00008002395,0.0008794449,0.002248795,0.003812582],"genre_scores_gemma":[0.7845328,0.0004386823,0.194913,0.000561083,0.0001140947,0.0004425076,0.003425788,0.0003794032,0.01519268],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01319145,"threshold_uncertainty_score":0.02622938,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09607990330988486,"score_gpt":0.3090844461013811,"score_spread":0.2130045427914963,"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."}}