{"id":"W3196070880","doi":"10.48550/arxiv.2111.05196","title":"NATURE: Natural Auxiliary Text Utterances for Realistic Spoken Language Evaluation","year":2021,"lang":"en","type":"article","venue":"arXiv (Cornell University)","topic":"Topic Modeling","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"","keywords":"Computer science; Utterance; Set (abstract data type); Spoken language; Simple (philosophy); Natural language; Natural language processing; Semantics (computer science); Natural language understanding; Artificial intelligence; Speech recognition; Programming language","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":[0.005466606,0.002577191,0.001067037,0.001282635,0.0007668918,0.002104872,0.002703219,0.0016758,0.004769307],"category_scores_gemma":[0.01967282,0.0004564397,0.0008839774,0.0009493984,0.0007272547,0.002589505,0.002244306,0.002096136,0.004073781],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001223337,"about_ca_system_score_gemma":0.001313283,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007594735,"about_ca_topic_score_gemma":0.01172482,"domain_scores_codex":[0.9943376,0.002919307,0.0004185191,0.001030624,0.001053221,0.0002406807],"domain_scores_gemma":[0.9928949,0.003641553,0.0003290342,0.001499417,0.001332994,0.0003020188],"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":[0.003730747,0.002295271,0.01583412,0.00307655,0.000658106,0.000907794,0.002139241,0.1913301,0.06336689,0.008461026,0.2115315,0.4966686],"study_design_scores_gemma":[0.0003335657,0.001109037,0.007423936,0.0001446038,0.0001106012,0.0004392762,0.001055766,0.8843183,0.05301591,0.01001319,0.04186076,0.000174977],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.4124655,0.003222187,0.3979337,0.001718537,0.002282041,0.002095415,0.06788743,0.0947464,0.01764882],"genre_scores_gemma":[0.6114268,0.0004216773,0.2505214,0.0005518675,0.0001950183,0.00205336,0.1262938,0.002899529,0.005636517],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.007594735,"threshold_uncertainty_score":0.02891052,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05376264222521476,"score_gpt":0.2216626485356336,"score_spread":0.1679000063104188,"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."}}