{"id":"W4399802498","doi":"10.1016/j.asoc.2024.111893","title":"Class conditioned text generation with style attention mechanism for embracing diversity","year":2024,"lang":"en","type":"article","venue":"Applied Soft Computing","topic":"Topic Modeling","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":false,"ca_institutions":"","funders":"Institute for Information and Communications Technology Promotion; Ministry of Science and ICT, South Korea; National Research Foundation of Korea; Information Technology Research Centre; Ministry of Science, ICT and Future Planning","keywords":"Computer science; Fluency; Natural language generation; Artificial intelligence; Transformer; Class (philosophy); Adversarial system; Scope (computer science); Text generation; Natural language processing; Natural language; Language model; Machine learning; Linguistics; Programming language","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003194142,0.000130119,0.0001261552,0.00009253169,0.0006828267,0.0003345395,0.0002849845,0.00005939833,0.000002645035],"category_scores_gemma":[0.000008444948,0.0001270097,0.00004773894,0.0001999115,0.00001462766,0.0002797752,0.0003547264,0.0001188446,0.00002143473],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008037192,"about_ca_system_score_gemma":0.00004095534,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001207526,"about_ca_topic_score_gemma":0.000006138291,"domain_scores_codex":[0.9988043,0.00001790499,0.0001840996,0.0005193879,0.0002309572,0.0002433708],"domain_scores_gemma":[0.9994397,0.0001226511,0.00006897176,0.000240732,0.00007953132,0.00004845512],"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":[0.000003596721,0.0000138502,0.0000213461,0.00006481678,0.00003441902,0.000005336042,0.001159938,0.01016147,0.01950888,0.9367526,0.0001158529,0.03215795],"study_design_scores_gemma":[0.0002862691,0.00002769863,0.00003916688,0.00004089294,0.00001678403,0.000009985473,0.00008983474,0.9797833,0.002477982,0.01700426,0.00005579216,0.0001680661],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1172394,0.00001593846,0.8805984,0.0002529266,0.0003688865,0.000308057,0.000001784996,0.000479854,0.0007347999],"genre_scores_gemma":[0.8342533,3.472978e-7,0.1651947,0.0002423486,0.0002139702,0.00001232568,0.00001845383,0.00001153913,0.00005297234],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9696218,"threshold_uncertainty_score":0.5251821,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02358681782272002,"score_gpt":0.2337100973111561,"score_spread":0.2101232794884361,"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."}}