{"id":"W6928942248","doi":"10.48448/mfka-vc24","title":"DuNST: Dual Noisy Self Training for Semi-Supervised Controllable Text Generation","year":2022,"lang":"en","type":"other","venue":"Underline Science Inc.","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Text generation; Fluency; Generalization; Space (punctuation); Process (computing); Construct (python library); Language model; Dual (grammatical number)","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":[0.001769508,0.001296553,0.000910435,0.0005868769,0.0005406901,0.0009301087,0.002732482,0.001624979,0.003986874],"category_scores_gemma":[0.004840905,0.000668934,0.0009557451,0.0004376537,0.001235659,0.002175113,0.002335564,0.00248549,0.002121056],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000797129,"about_ca_system_score_gemma":0.0008684753,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002331782,"about_ca_topic_score_gemma":0.005119611,"domain_scores_codex":[0.9988049,0.0003998916,0.00005526981,0.000459405,0.0001895865,0.00009096831],"domain_scores_gemma":[0.9973223,0.001587243,0.0001602212,0.0005081438,0.0002831679,0.000138894],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0005974444,0.000498454,0.002276078,0.0003773254,0.0001369183,0.0003104182,0.0004810938,0.3537216,0.02874885,0.0102431,0.01977092,0.5828377],"study_design_scores_gemma":[0.00002570948,0.00006140674,0.0001121506,0.000009461164,0.000006272681,0.00002935247,0.00001692549,0.9899368,0.004301338,0.00405549,0.001434482,0.00001065362],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02745158,0.000526981,0.9540447,0.0003247179,0.0001565149,0.0001556221,0.0003821852,0.01459222,0.002365517],"genre_scores_gemma":[0.5494688,0.0002565998,0.4309625,0.001038002,0.0001876261,0.000714153,0.003526734,0.002237321,0.01160827],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003986874,"threshold_uncertainty_score":0.01333737,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02199196829639992,"score_gpt":0.2826844332052911,"score_spread":0.2606924649088912,"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."}}