{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0002178523,0.0002417251,0.0003726125,0.0001080911,0.00006570738,0.0001972598,0.002402661,0.0002104508,0.0000233821],"category_scores_gemma":[0.000739759,0.0002580584,0.00005902607,0.00008883825,0.00005067787,0.00006184082,0.002822452,0.0003621982,0.00003367002],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005689555,"about_ca_system_score_gemma":0.000662004,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009122794,"about_ca_topic_score_gemma":0.00001528566,"domain_scores_codex":[0.9977296,0.00007251936,0.0005932561,0.0008983238,0.0005228986,0.0001834158],"domain_scores_gemma":[0.9965972,0.000258888,0.0004734462,0.001884762,0.0007183728,0.00006736271],"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":[0.000004704902,0.00003440602,0.0004453851,0.00006534631,0.00006237205,0.000004791981,0.0001902297,0.9778287,0.00009925945,0.01699262,0.00290631,0.001365807],"study_design_scores_gemma":[0.0002037295,0.00001281247,0.0005458228,0.00008791415,0.00003442899,0.000001006738,0.000005837819,0.9305215,0.0001954982,0.06729671,0.0008638701,0.0002308339],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01553711,0.0003972509,0.9752601,0.0001339299,0.006250766,0.0002477713,0.001729466,0.00007259264,0.0003710483],"genre_scores_gemma":[0.4768005,0.000005353434,0.5156596,0.00006916194,0.00139164,0.000001830312,0.006009672,0.00001302083,0.00004919215],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.4612634,"threshold_uncertainty_score":0.9999872,"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."}}