{"id":"W4385570307","doi":"10.18653/v1/2023.acl-long.488","title":"DuNST: Dual Noisy Self Training for Semi-Supervised Controllable Text Generation","year":2023,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Controllability; Text generation; Fluency; Generalization; Artificial intelligence; Language model; Construct (python library); Process (computing); Exploit; Dual (grammatical number); Space (punctuation); Boundary (topology); Natural language processing; Machine learning; Mathematics","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004473901,0.0001021626,0.0001460977,0.00008730585,0.0001670609,0.0001836248,0.0002880215,0.00005880931,0.00002819048],"category_scores_gemma":[0.00004965335,0.0000935144,0.00005876277,0.0002913939,0.000006434635,0.0003624091,0.00008525832,0.00005191275,0.0001015585],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002715745,"about_ca_system_score_gemma":0.00009378557,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001509699,"about_ca_topic_score_gemma":0.00002096663,"domain_scores_codex":[0.9988813,0.00002696424,0.0002161205,0.0003614902,0.0001875029,0.0003265775],"domain_scores_gemma":[0.9993703,0.0001157483,0.00003293772,0.0003334291,0.00007934204,0.00006826689],"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":[0.00001919023,0.0001065319,0.0002628572,0.00009273263,0.0001565253,0.00004607639,0.02563043,0.08187962,0.1682092,0.395652,0.04977763,0.2781672],"study_design_scores_gemma":[0.0007600445,0.00003327971,0.00002807022,0.000003462132,0.000004295283,0.000003781659,0.00009377411,0.9896727,0.00242235,0.0008943075,0.005969602,0.0001143936],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07628775,0.00001953332,0.9164777,0.002192181,0.0005481718,0.0003181581,0.000002424626,0.0008448345,0.003309228],"genre_scores_gemma":[0.8188734,0.000004897113,0.1759421,0.0008500705,0.000478438,0.00008514093,0.00001258312,0.00001279228,0.003740615],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.907793,"threshold_uncertainty_score":0.3813406,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07735932174670801,"score_gpt":0.2725283510649023,"score_spread":0.1951690293181942,"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."}}