{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000524663,0.0002778795,0.0004544428,0.00009568889,0.0001811938,0.0002761866,0.001523875,0.0001121273,0.0001330477],"category_scores_gemma":[0.0007036166,0.0002135235,0.0001558984,0.0008914396,0.0001824699,0.0005693935,0.0002856302,0.0005252447,0.00007527615],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003575278,"about_ca_system_score_gemma":0.00008981391,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006040139,"about_ca_topic_score_gemma":0.00001252196,"domain_scores_codex":[0.997791,0.00007490234,0.0005937507,0.0006573114,0.0004864495,0.0003966125],"domain_scores_gemma":[0.9989731,0.0001055139,0.0001769995,0.0002038993,0.0004019147,0.0001385686],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0007232226,0.0003080434,0.002502823,0.00012122,0.00005062509,0.000004944583,0.01731383,0.007094559,0.2594021,0.4060743,0.0004502815,0.3059541],"study_design_scores_gemma":[0.000178758,0.0005201756,0.0002001175,0.0003479485,0.0000199673,0.000001727316,0.001692083,0.5780625,0.4128878,0.004533151,0.001149804,0.0004059416],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3402278,0.0001212887,0.6147052,0.02777738,0.0008773186,0.001687882,0.000006791161,0.0002709717,0.01432534],"genre_scores_gemma":[0.9958395,0.00006210208,0.003410482,0.0003979541,0.0001649104,0.00001033471,4.612966e-7,0.00001661198,0.00009769368],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6556116,"threshold_uncertainty_score":0.8707235,"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."}}