{"id":"W7111753261","doi":"","title":"MTUncertainty:Assessing the Need for Post-editing of Machine Translation Outputs by Fine-tuning OpenAI LLMs","year":2023,"lang":"en","type":"article","venue":"Research Explorer (The University of Manchester)","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Open Text (Canada)","funders":"Dell Technologies","keywords":"Machine translation; Translation (biology); Quality (philosophy); Process (computing); Task (project management); Binary number; Work (physics)","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":[0.008395037,0.002386636,0.001498416,0.001791788,0.001022767,0.002943927,0.002561256,0.002551151,0.003115876],"category_scores_gemma":[0.03863371,0.0007731462,0.001239605,0.001609638,0.001093513,0.004420487,0.00292392,0.00342576,0.002924721],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001493265,"about_ca_system_score_gemma":0.001908556,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01159418,"about_ca_topic_score_gemma":0.01182689,"domain_scores_codex":[0.9940692,0.002118531,0.0006866033,0.001546421,0.001270483,0.0003088407],"domain_scores_gemma":[0.9795076,0.01190476,0.001506857,0.003372543,0.003058462,0.0006497591],"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":[0.004475152,0.001394089,0.03811031,0.002290509,0.001171839,0.0007477835,0.002034649,0.2444623,0.06493261,0.003116268,0.0220799,0.6151845],"study_design_scores_gemma":[0.0002334338,0.0009938945,0.01028769,0.0001170856,0.0003745569,0.0003494807,0.0004272895,0.9272243,0.04609171,0.00373347,0.01002416,0.000142839],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6205522,0.005922219,0.2908634,0.001356989,0.0007600252,0.0007858897,0.003829412,0.06433778,0.01159211],"genre_scores_gemma":[0.8396655,0.000586548,0.1407967,0.0005282029,0.00009935563,0.0004636146,0.01114823,0.002826638,0.003885099],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01159418,"threshold_uncertainty_score":0.04439771,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09153001966312556,"score_gpt":0.3451427517996847,"score_spread":0.2536127321365592,"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."}}