{"id":"W2980073313","doi":"10.1162/coli_a_00363","title":"Scalable Micro-planned Generation of Discourse from Structured Data","year":2019,"lang":"en","type":"article","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Topic Modeling","field":"Computer Science","cited_by":23,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"","keywords":"Computer science; Natural language processing; Interpretability; Scalability; Artificial intelligence; Natural language generation; Sentence; Pipeline (software); Paragraph; Fluency; Natural language understanding; Data manipulation language; Natural language; Information retrieval; Programming language; Database; World Wide Web","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":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0003594439,0.00008911842,0.0001203198,0.00009779821,0.0003803121,0.000475001,0.002706296,0.00004359189,0.004093875],"category_scores_gemma":[0.0001225659,0.00008942572,0.00001980105,0.0002608341,0.00004275248,0.0006627252,0.002352022,0.0001238831,0.002616088],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003916534,"about_ca_system_score_gemma":0.000005673573,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003411695,"about_ca_topic_score_gemma":8.63755e-7,"domain_scores_codex":[0.998625,0.0001579626,0.000214659,0.0005015688,0.0003008612,0.0001998832],"domain_scores_gemma":[0.9980997,0.00001445849,0.0001055192,0.001493826,0.0002117444,0.0000747899],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00006195677,0.0001867827,0.0001085551,0.00007998387,0.0001086363,0.00001055297,0.002947751,0.003694553,0.5574244,0.01760019,0.159977,0.2577996],"study_design_scores_gemma":[0.001121165,0.0002151449,0.001109712,0.00005046875,0.00001737758,0.00003362812,0.0002415432,0.5142909,0.02138896,0.0009900663,0.4601786,0.0003623628],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5050892,0.0001460248,0.4776255,0.001083883,0.0004806573,0.0005441492,0.0006705053,0.000597647,0.01376245],"genre_scores_gemma":[0.9763845,0.00001655533,0.01947381,0.00008262337,0.0001545947,7.952254e-9,0.003107287,0.0003088365,0.0004718016],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5360355,"threshold_uncertainty_score":0.9981605,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06693568368884965,"score_gpt":0.266282299033941,"score_spread":0.1993466153450913,"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."}}