{"id":"W4297841482","doi":"10.21437/interspeech.2022-760","title":"Low-bit Shift Network for End-to-End Spoken Language Understanding","year":2022,"lang":"en","type":"article","venue":"Interspeech 2022","topic":"Neural Networks and Applications","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Huawei Technologies (Canada)","funders":"","keywords":"Computer science; End-to-end principle; Computer network","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":[0.0003609229,0.0001311214,0.0001436079,0.00008585459,0.0004836189,0.0001463637,0.001078671,0.00002270446,0.0005839712],"category_scores_gemma":[0.0000140349,0.0001386958,0.0001137404,0.000671914,0.00002135171,0.0001335258,0.0008775043,0.0002352544,0.00003407489],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002529813,"about_ca_system_score_gemma":0.00003832141,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003693823,"about_ca_topic_score_gemma":0.00005463499,"domain_scores_codex":[0.9986075,0.00004990969,0.0001985871,0.0004557281,0.0002728263,0.0004154593],"domain_scores_gemma":[0.9990934,0.0002480386,0.00007144469,0.0004578832,0.00001598035,0.0001132903],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00008267831,0.0001973445,0.0001938645,0.00002373661,0.00008599097,0.00009687681,0.006110519,0.01203262,0.002449861,0.5857924,0.3438093,0.04912483],"study_design_scores_gemma":[0.002823927,0.001867137,0.0006461161,0.0001990894,0.00009099892,0.0001804458,0.0136275,0.1729693,0.006685094,0.1532959,0.6451306,0.002483759],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02339223,0.0001889222,0.9625043,0.009541193,0.001142835,0.0007090361,0.00007411413,0.0002563653,0.002190975],"genre_scores_gemma":[0.9864455,0.000003185327,0.008683696,0.002598348,0.0003551195,0.0003524583,0.00002927402,0.0000216997,0.001510673],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9630533,"threshold_uncertainty_score":0.6394075,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02692692012041936,"score_gpt":0.2755905298264654,"score_spread":0.248663609706046,"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."}}