{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.000844454,0.0002926244,0.0002785136,0.0002401732,0.0004063959,0.000125613,0.0005371885,0.0002436322,0.00104817],"category_scores_gemma":[0.0003154088,0.0002825019,0.00009062597,0.0002703713,0.0002298111,0.000009753868,0.0002427307,0.0002232356,0.00002421205],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007264513,"about_ca_system_score_gemma":0.0007525442,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002548805,"about_ca_topic_score_gemma":0.0001083978,"domain_scores_codex":[0.9981242,0.00004832578,0.0003365326,0.0005578635,0.0004493364,0.0004837508],"domain_scores_gemma":[0.9989349,0.00002446923,0.0002775823,0.0005312931,0.0001124542,0.0001193619],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00005771817,0.0001918016,0.0002102569,0.0002400021,0.0002400628,0.000006223971,0.001130806,0.007099842,0.242259,0.002024243,0.7285412,0.01799892],"study_design_scores_gemma":[0.0009289955,0.0003197449,0.000003936776,0.00001079796,0.00003652733,0.00001902907,0.0002008102,0.1724419,0.001586807,0.00001613934,0.8240933,0.0003420807],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"other","genre_gemma":"other","genre_scores_codex":[0.01271641,0.001883319,0.0608619,0.001397339,0.004187274,0.004561359,0.001049197,0.0007268876,0.9126163],"genre_scores_gemma":[0.1103726,0.0003397854,0.2329034,0.005086654,0.007083861,0.000554221,0.009136017,0.001037184,0.6334863],"genre_candidate":"other","genre_consensus":"other","teacher_disagreement_score":0.27913,"threshold_uncertainty_score":0.9999627,"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."}}