{"id":"W4399125980","doi":"10.1109/trustcom60117.2023.00347","title":"A Large-scale Non-standard English Database and Transformer-based Translation System","year":2023,"lang":"en","type":"article","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"York University","funders":"","keywords":"Computer science; Natural language processing; Transformer; Readability; Artificial intelligence; Machine translation; Slang; Linguistics; Programming language","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":[0.00123389,0.001084769,0.001238044,0.002803086,0.0009603528,0.001584642,0.002236414,0.0007685214,0.01229353],"category_scores_gemma":[0.003963072,0.0007006197,0.0007915809,0.002033666,0.000577884,0.003627937,0.003122922,0.001067586,0.01273315],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008296572,"about_ca_system_score_gemma":0.002091225,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00457584,"about_ca_topic_score_gemma":0.005203184,"domain_scores_codex":[0.9986554,0.0001783419,0.0002105847,0.0005628853,0.0003140013,0.00007866182],"domain_scores_gemma":[0.9979557,0.0004318317,0.0001104265,0.0006110531,0.0007287956,0.0001622937],"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":[0.001032818,0.0009902717,0.004302693,0.001124048,0.0001963171,0.002448292,0.001315282,0.004235227,0.1335071,0.01003394,0.1239859,0.7168281],"study_design_scores_gemma":[0.001056383,0.00100754,0.009424072,0.0001980393,0.0005072982,0.005635599,0.002819733,0.3958829,0.3038658,0.017891,0.2612148,0.000496893],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.09476096,0.0006914044,0.6455878,0.000803589,0.000493662,0.001449182,0.02100362,0.2199931,0.01521659],"genre_scores_gemma":[0.2777446,0.0004359088,0.6211239,0.0007899159,0.0001292143,0.000771229,0.07872991,0.005769272,0.01450604],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01229353,"threshold_uncertainty_score":0.04112589,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01207438424063391,"score_gpt":0.2595191302919702,"score_spread":0.2474447460513363,"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."}}