{"id":"W2895279374","doi":"10.1162/coli_a_00363","title":"Scalable Micro-planned Generation of Discourse from Structured Data","year":2019,"lang":"en","type":"preprint","venue":"Computational Linguistics","topic":"Topic Modeling","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"","keywords":"Computer science; Interpretability; Natural language processing; Scalability; Artificial intelligence; Natural language generation; Sentence; Pipeline (software); Paragraph; Fluency; Text simplification; Natural language understanding; Robustness (evolution); Natural language; Programming language; Database","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":[0.001824372,0.001003904,0.0007394824,0.001697289,0.0006893257,0.001653522,0.001691613,0.000788645,0.007651654],"category_scores_gemma":[0.009486726,0.0005961796,0.001222102,0.001325489,0.0007098676,0.002630942,0.002192564,0.001221408,0.004386621],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007892889,"about_ca_system_score_gemma":0.001933577,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002679475,"about_ca_topic_score_gemma":0.004420707,"domain_scores_codex":[0.9986174,0.0004328662,0.0001035243,0.0004844868,0.0003039159,0.00005773268],"domain_scores_gemma":[0.995653,0.002610545,0.0002216105,0.0007322887,0.0006560761,0.0001263688],"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":[0.0006422142,0.0002972847,0.003181103,0.001492601,0.0001536114,0.001017334,0.002867715,0.03825135,0.05415381,0.05084812,0.07385127,0.7732434],"study_design_scores_gemma":[0.0001494971,0.0001490954,0.0009240545,0.0001088072,0.00007599808,0.0003946891,0.0007509688,0.7789135,0.07595064,0.06052438,0.08197053,0.00008784291],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01159721,0.0002391173,0.9495867,0.0004327829,0.0001281203,0.0003131178,0.004045073,0.0310253,0.002632587],"genre_scores_gemma":[0.0986229,0.0001929592,0.8817062,0.0001621944,0.00007755972,0.0003898083,0.0137347,0.002019094,0.003094569],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.007651654,"threshold_uncertainty_score":0.02559733,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08137583821686917,"score_gpt":0.3230469773943666,"score_spread":0.2416711391774974,"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."}}