{"id":"W4385565354","doi":"10.18653/v1/2023.acl-long.526","title":"Learning to Imagine: Visually-Augmented Natural Language Generation","year":2023,"lang":"en","type":"article","venue":"","topic":"Multimodal Machine Learning Applications","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"National Natural Science Foundation of China","keywords":"Computer science; Paragraph; Natural language; Artificial intelligence; Transformer; Augmented reality; Sentence; Natural language processing; Code (set theory); Human–computer interaction; Programming language; 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":[],"category_scores_codex":[0.0002162672,0.00009169162,0.0000732189,0.0001792247,0.0001594295,0.0001639364,0.0004358505,0.00002126235,0.00004010043],"category_scores_gemma":[0.0001251579,0.00008450847,0.00002996534,0.0009951461,0.000007461802,0.0001921066,0.0002669836,0.0001810026,0.002208155],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003099892,"about_ca_system_score_gemma":0.00001805386,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003115227,"about_ca_topic_score_gemma":0.00002264689,"domain_scores_codex":[0.9990681,0.00005693032,0.0001254744,0.0003256989,0.0002038647,0.000219909],"domain_scores_gemma":[0.999463,0.00005260409,0.00003087278,0.0003196674,0.00005338766,0.00008053536],"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":[0.000002849075,0.00004501673,0.003391944,0.000009111224,0.00001962072,0.00001675617,0.005715028,0.03624595,0.5138891,0.01655805,0.01369212,0.4104145],"study_design_scores_gemma":[0.0001110958,0.00002542931,0.02249153,0.000002438909,0.000001229879,0.000002766528,0.00007210416,0.9719797,0.002971762,0.00001823252,0.002208822,0.0001148584],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6322293,0.00001749533,0.3579767,0.005963779,0.0001959558,0.0002005163,4.704884e-7,0.001886962,0.001528784],"genre_scores_gemma":[0.9448292,0.000001222509,0.049121,0.0006774462,0.0001129944,0.00005061585,0.00003955502,0.0000110449,0.005156875],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9357338,"threshold_uncertainty_score":0.9985687,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01060861406612697,"score_gpt":0.3164279157877798,"score_spread":0.3058193017216528,"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."}}