{"id":"W4385574346","doi":"10.18653/v1/2022.emnlp-main.366","title":"Rethinking Style Transformer with Energy-based Interpretation: Adversarial Unsupervised Style Transfer using a Pretrained Model","year":2022,"lang":"en","type":"article","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Kootenay Association for Science & Technology","funders":"Institute for Information and Communications Technology Promotion; Ministry of Science and ICT, South Korea; Korea Advanced Institute of Science and Technology; National Research Foundation of Korea; National Research Foundation","keywords":"Transformer; Computer science; Adversarial system; Style (visual arts); Energy transfer; Natural language processing; Artificial intelligence; Interpretation (philosophy); Engineering; Programming language; Art; Electrical engineering; Visual arts; Voltage","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":[0.00129963,0.001297169,0.001085172,0.0004924639,0.000372852,0.001098878,0.001792876,0.00143911,0.004353583],"category_scores_gemma":[0.002816929,0.0005615464,0.00128432,0.0004904958,0.0007544743,0.00182803,0.001782389,0.002893415,0.002540242],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004611372,"about_ca_system_score_gemma":0.0005205545,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001927406,"about_ca_topic_score_gemma":0.004085417,"domain_scores_codex":[0.9994959,0.00016089,0.00002360496,0.0001634529,0.0001027283,0.00005345218],"domain_scores_gemma":[0.9988569,0.0005404949,0.00005615071,0.0003552156,0.0001234021,0.00006778238],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0004800532,0.0003158299,0.001577982,0.000154377,0.0002824998,0.0002512082,0.0002104184,0.3648266,0.02344029,0.01096771,0.01489314,0.5825999],"study_design_scores_gemma":[0.0000136322,0.00004572534,0.0001152375,0.000008881965,0.00001558292,0.00004278201,0.000009580495,0.9914302,0.002051127,0.00552469,0.0007337346,0.000008849886],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.04362425,0.001385436,0.9436243,0.0005514098,0.0005541329,0.0001000892,0.000276751,0.00416405,0.005719618],"genre_scores_gemma":[0.7894262,0.0007595497,0.1880907,0.001053493,0.0003647885,0.0001470076,0.001118878,0.000909899,0.01812943],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.004353583,"threshold_uncertainty_score":0.01456416,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01765276557485128,"score_gpt":0.2400949860414793,"score_spread":0.222442220466628,"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."}}