{"id":"W4287890446","doi":"10.18653/v1/2022.naacl-industry.30","title":"Adversarial Text Normalization","year":2022,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Adversarial system; Normalization (sociology); Computer science; Computational linguistics; Artificial intelligence; Maya; Natural language processing; Linguistics; History; Sociology; Philosophy; Anthropology; Archaeology","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":[0.002848379,0.001845897,0.001332253,0.001270816,0.0008317874,0.001855565,0.002287299,0.001985884,0.01703224],"category_scores_gemma":[0.009871025,0.0007320759,0.001165139,0.001429611,0.00108575,0.002736775,0.003483934,0.003393112,0.02275615],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006621274,"about_ca_system_score_gemma":0.0008856129,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002233283,"about_ca_topic_score_gemma":0.003369017,"domain_scores_codex":[0.997842,0.0007507367,0.00007941086,0.0006727565,0.0004852523,0.0001698685],"domain_scores_gemma":[0.9969543,0.001414261,0.0001178815,0.0009724439,0.0004435433,0.00009757394],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0003832162,0.0001814683,0.0005733063,0.0003467645,0.0002152512,0.0002836719,0.0001219698,0.09833627,0.01456832,0.03570068,0.2818055,0.5674835],"study_design_scores_gemma":[0.00004487464,0.00007506135,0.0004130403,0.0000881606,0.00005135682,0.0003365537,0.00005978793,0.864791,0.01510877,0.05954815,0.05943815,0.00004515583],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.005506014,0.00375724,0.9595456,0.002743542,0.002811636,0.0002074509,0.002528055,0.009373717,0.01352667],"genre_scores_gemma":[0.2796806,0.005504437,0.5407698,0.00415281,0.003864681,0.0009608628,0.02206836,0.004669709,0.1383288],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01703224,"threshold_uncertainty_score":0.05697852,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01375158304709666,"score_gpt":0.2157998253951286,"score_spread":0.202048242348032,"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."}}