{"id":"W4389009557","doi":"10.18653/v1/2023.inlg-main.36","title":"Mod-D2T: A Multi-layer Dataset for Modular Data-to-Text Generation","year":2023,"lang":"en","type":"article","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"European Commission","keywords":"Computer science; Modular design; Fluency; Pipeline (software); Text generation; Leverage (statistics); Artificial intelligence; Documentation; Natural language processing; Code (set theory); Data mining; Information retrieval; Programming language","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":[0.001499832,0.002242264,0.0005771178,0.00208567,0.001084847,0.001662128,0.003883174,0.002475566,0.0141923],"category_scores_gemma":[0.0080512,0.0006159939,0.001946561,0.002049158,0.0009270885,0.002138812,0.002531786,0.002440301,0.01327585],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001206857,"about_ca_system_score_gemma":0.001497109,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007698634,"about_ca_topic_score_gemma":0.02000494,"domain_scores_codex":[0.998818,0.0002849041,0.0001427744,0.0003954236,0.000280305,0.00007865182],"domain_scores_gemma":[0.9968989,0.001257499,0.0002080215,0.001067546,0.0003806075,0.0001874505],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0007363496,0.0006608226,0.007427719,0.002894007,0.0003138073,0.0007371365,0.0004068481,0.01739393,0.01074678,0.007151093,0.8397008,0.1118308],"study_design_scores_gemma":[0.001516959,0.0007164484,0.01655376,0.0004982924,0.0002253119,0.002038686,0.0008440512,0.1683988,0.04689193,0.03274644,0.7292569,0.0003124467],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.04192457,0.001042693,0.04826348,0.001173455,0.0006309089,0.001199846,0.8447106,0.0470856,0.01396881],"genre_scores_gemma":[0.02826639,0.0001449291,0.05804899,0.000313643,0.00003746267,0.001177413,0.9077705,0.00104044,0.003200211],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.0141923,"threshold_uncertainty_score":0.04747802,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1976351903331568,"score_gpt":0.3922437539936958,"score_spread":0.194608563660539,"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."}}