{"id":"W2963924362","doi":"","title":"Natural Language Generation in Dialogue using Lexicalized and Delexicalized Data","year":2017,"lang":"en","type":"article","venue":"arXiv (Cornell University)","topic":"Speech and dialogue systems","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Natural language generation; Natural language processing; Artificial intelligence; Natural language; Sentence; Grammar; Language model; Encoder; Task (project management); Value (mathematics); Recurrent neural network; Speech recognition; Artificial neural network; Linguistics; Machine learning","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":[0.0002555911,0.00009883173,0.0001524006,0.00008665762,0.0002410441,0.000217188,0.001217979,0.0000666632,0.000003765125],"category_scores_gemma":[0.0001283598,0.0001003442,0.00002490373,0.0001342973,0.00008418593,0.001148277,0.0007225201,0.00009803189,0.00001069761],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003958781,"about_ca_system_score_gemma":0.00004610269,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001777878,"about_ca_topic_score_gemma":0.001214322,"domain_scores_codex":[0.9990436,0.00009421028,0.0001050147,0.000506782,0.00005060687,0.0001997756],"domain_scores_gemma":[0.9985055,0.00003499735,0.00009640733,0.001251111,0.00002493838,0.00008703734],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0005621939,0.0005273643,0.1264019,0.0001358405,0.000214398,0.008101081,0.003495439,0.009010485,0.08843481,0.7332419,0.002165622,0.02770905],"study_design_scores_gemma":[0.001155753,0.00001267733,0.004022556,0.00001106201,0.000007808798,0.00001239842,0.00003354688,0.992844,0.0003614661,0.001229807,0.000154215,0.0001546959],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8847683,0.0001297725,0.114156,0.00006392338,0.0003018169,0.0001119885,0.000008450487,0.00004485311,0.0004148444],"genre_scores_gemma":[0.9973873,0.0000198092,0.002293251,0.00005745492,0.00009536713,1.211823e-7,0.00002836631,0.000004400478,0.0001139679],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9838336,"threshold_uncertainty_score":0.4091919,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1867842812394854,"score_gpt":0.2470712434276623,"score_spread":0.06028696218817686,"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."}}