{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005135179,0.000983484,0.0003204125,0.0003402644,0.0002206143,0.0008362318,0.001380619,0.0007482864,0.008078459],"category_scores_gemma":[0.002191193,0.0003102217,0.0007491384,0.0001805454,0.0005435326,0.00172191,0.001400175,0.001123196,0.002165987],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003798432,"about_ca_system_score_gemma":0.0003859092,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001584623,"about_ca_topic_score_gemma":0.002793283,"domain_scores_codex":[0.9997054,0.00006990744,0.00001166046,0.0001091133,0.00007426798,0.00002962527],"domain_scores_gemma":[0.9995064,0.0002220472,0.00002954495,0.0001329065,0.00006935761,0.00003979926],"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":[0.0006211344,0.0003561782,0.001279843,0.000461034,0.0001181281,0.0006143454,0.0007792866,0.07324585,0.1445384,0.02184685,0.02499865,0.7311403],"study_design_scores_gemma":[0.0000972741,0.0002610832,0.0007886295,0.00003225241,0.00004870154,0.0005020989,0.0001677426,0.8616497,0.0881341,0.02608563,0.02217628,0.0000565201],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02410647,0.0002147433,0.9480213,0.0002126584,0.0001600612,0.0001418735,0.0004810384,0.02053905,0.006122837],"genre_scores_gemma":[0.4382744,0.0001874127,0.5481204,0.000303726,0.00005839002,0.0001947958,0.001976752,0.00120991,0.009674129],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.008078459,"threshold_uncertainty_score":0.0270251,"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."}}