{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001719418,0.000631402,0.0004893065,0.0003985359,0.0003453999,0.0009860717,0.001045779,0.0009416304,0.001938038],"category_scores_gemma":[0.007882839,0.0004490459,0.0007044308,0.0002516115,0.0006739945,0.001775914,0.001246152,0.001660309,0.0008432817],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000571508,"about_ca_system_score_gemma":0.0007294057,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002602618,"about_ca_topic_score_gemma":0.003791185,"domain_scores_codex":[0.9989055,0.0005595851,0.0000524534,0.0003043189,0.0001163991,0.00006183256],"domain_scores_gemma":[0.9967384,0.002331985,0.0001642137,0.0003395091,0.000336015,0.00008994196],"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":[0.0008769452,0.0005277668,0.005175702,0.0004512354,0.0001800845,0.001057285,0.002226433,0.4663402,0.06907188,0.0402997,0.006632984,0.4071599],"study_design_scores_gemma":[0.00002122761,0.00006502049,0.0002816285,0.00001407091,0.00001587049,0.00007903788,0.00005345131,0.98019,0.00688069,0.01098889,0.001393143,0.000016996],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08891662,0.0003086569,0.9027523,0.0006116493,0.0001424303,0.0001214529,0.0003288946,0.003908117,0.002909913],"genre_scores_gemma":[0.7899582,0.0001678027,0.2045866,0.0003132122,0.00006226257,0.0001877135,0.000992969,0.0003844806,0.003346708],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002602618,"threshold_uncertainty_score":0.009093225,"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."}}