{"id":"W2885765530","doi":"10.18653/v1/p19-1041","title":"Disentangled Representation Learning for Non-Parallel Text Style Transfer","year":2019,"lang":"en","type":"preprint","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":33,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; Nvidia","keywords":"Fluency; Representation (politics); Computer science; Style (visual arts); Task (project management); Simple (philosophy); Artificial intelligence; Natural language processing; Space (punctuation); Adversarial system; Latent variable; Transfer (computing); Transfer of learning; Machine learning; Linguistics","routes":{"ca_aff":true,"ca_fund":true,"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":[0.002316319,0.001568176,0.001099959,0.000784562,0.0005056433,0.001169443,0.001478257,0.001344935,0.002947072],"category_scores_gemma":[0.006244321,0.0006224651,0.00122389,0.001045226,0.001180487,0.003649349,0.003011725,0.003255221,0.00181407],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006614582,"about_ca_system_score_gemma":0.0006238935,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001110982,"about_ca_topic_score_gemma":0.001615955,"domain_scores_codex":[0.9987984,0.0005857987,0.000044317,0.0003032807,0.0001809026,0.00008738582],"domain_scores_gemma":[0.9974306,0.00133577,0.000208408,0.0007291086,0.0001826365,0.000113368],"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":[0.0003937358,0.0004094712,0.001602235,0.0002147,0.0002405052,0.0002224737,0.000374039,0.5756318,0.02550047,0.03817801,0.00549877,0.3517338],"study_design_scores_gemma":[0.00001341068,0.00004363159,0.0001568239,0.000005588546,0.00001206899,0.0000241287,0.000009523006,0.9747395,0.002358784,0.02186627,0.0007603954,0.000009844245],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01864759,0.0003150378,0.9785103,0.0001904317,0.00006418946,0.00003699148,0.0001020655,0.0009168569,0.001216661],"genre_scores_gemma":[0.7079774,0.0007342121,0.2758645,0.0003663934,0.000422811,0.000340988,0.001284755,0.0005050875,0.01250381],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.002947072,"threshold_uncertainty_score":0.01225007,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03807439985645557,"score_gpt":0.2954949955950513,"score_spread":0.2574205957385957,"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."}}