{"id":"W2998659916","doi":"10.1609/aaai.v34i05.6355","title":"Revision in Continuous Space: Unsupervised Text Style Transfer without Adversarial Learning","year":2020,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":42,"is_retracted":false,"has_abstract":true,"ca_institutions":"Polytechnique Montréal","funders":"National Natural Science Foundation of China; National Science Foundation","keywords":"Computer science; Sentence; Adversarial system; Representation (politics); Artificial intelligence; Space (punctuation); Inference; Key (lock); Style (visual arts); Encoder; Transfer of learning; Natural language processing; Transfer (computing); Machine learning","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":[0.001391034,0.001009216,0.0007788891,0.0004529232,0.0002956861,0.0006731273,0.00143265,0.0008852446,0.002933787],"category_scores_gemma":[0.004400633,0.0003778846,0.0008332732,0.0004021606,0.0008700549,0.001530213,0.001309284,0.00171442,0.001230271],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004472669,"about_ca_system_score_gemma":0.000499318,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0008777894,"about_ca_topic_score_gemma":0.001089656,"domain_scores_codex":[0.999257,0.0002471883,0.00003546836,0.000223622,0.0001823013,0.00005443357],"domain_scores_gemma":[0.9983945,0.0007901291,0.0001640595,0.0003880647,0.000186416,0.00007685751],"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":[0.0003976448,0.0002010913,0.001177305,0.0001965912,0.0001686075,0.0002780616,0.0003021599,0.4646314,0.04102268,0.0216039,0.006809304,0.4632114],"study_design_scores_gemma":[0.00001781227,0.00006611955,0.0002096917,0.0000071394,0.00001301609,0.00005698264,0.00001158698,0.9834946,0.006398674,0.008568482,0.00114281,0.00001303487],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01396271,0.0001979352,0.9829636,0.0001220357,0.00008040898,0.00006044708,0.00006703471,0.001120807,0.001425176],"genre_scores_gemma":[0.6995942,0.0003581716,0.2855605,0.0005283657,0.0002765254,0.000253822,0.0005754838,0.0004891666,0.0123638],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002933787,"threshold_uncertainty_score":0.00981456,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04887968651990926,"score_gpt":0.2600740986570526,"score_spread":0.2111944121371434,"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."}}