{"id":"W2618015847","doi":"10.21437/interspeech.2017-1178","title":"ASR Error Management for Improving Spoken Language Understanding","year":2017,"lang":"en","type":"preprint","venue":"","topic":"Speech and dialogue systems","field":"Computer Science","cited_by":30,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"Agence Nationale de la Recherche","keywords":"Computer science; Word error rate; Spoken language; Encoder; Word (group theory); Artificial intelligence; Task (project management); Set (abstract data type); Conditional random field; Natural language processing; Speech recognition; State (computer science); Language model; Machine learning; Algorithm","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":[0.002649392,0.001399646,0.0009949247,0.001175785,0.0004416782,0.001424427,0.001463155,0.001202563,0.002956505],"category_scores_gemma":[0.01119506,0.0003465051,0.0005015805,0.0005538569,0.0008992879,0.002555627,0.001702047,0.001648893,0.001434293],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005448324,"about_ca_system_score_gemma":0.0007506498,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001804937,"about_ca_topic_score_gemma":0.001528299,"domain_scores_codex":[0.9966402,0.001018672,0.0002232237,0.0009646901,0.001008091,0.0001450537],"domain_scores_gemma":[0.9928536,0.004002213,0.0007533113,0.001022119,0.001239848,0.0001289399],"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":[0.0006265275,0.000189416,0.002778136,0.0003536007,0.0000813387,0.0002069659,0.0008267679,0.06989741,0.1266431,0.005541105,0.002453538,0.7904021],"study_design_scores_gemma":[0.00002905697,0.0002601235,0.002350564,0.00003521782,0.00007189611,0.0002909693,0.000168925,0.8654944,0.1209156,0.00717145,0.003155506,0.00005627722],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04869353,0.0005493473,0.9444976,0.0002062055,0.00006522419,0.00004543311,0.0001222438,0.004814896,0.00100534],"genre_scores_gemma":[0.646564,0.0003316774,0.3486371,0.0001432313,0.000108873,0.00008093989,0.0004571468,0.0006675856,0.003009432],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002956505,"threshold_uncertainty_score":0.0140115,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07849318842714537,"score_gpt":0.3097299478907526,"score_spread":0.2312367594636072,"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."}}