{"id":"W7076051120","doi":"10.23977/jaip.2025.080310","title":"An Empirical Analysis of Neural Network Machine Translation and Human Translation","year":2025,"lang":"en","type":"article","venue":"Journal of Artificial Intelligence Practice","topic":"Theoretical and Computational Physics","field":"Physics and Astronomy","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Machine translation; Translation (biology); Example-based machine translation; Sentence; Computer-assisted translation; Machine translation software usability; Vocabulary; Transfer-based machine translation","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"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":[0.0004818381,0.00008162951,0.00023372,0.0001376143,0.00009270266,0.00005062191,0.0000988383,0.00002754075,0.00007618501],"category_scores_gemma":[0.0000193959,0.00007117677,0.0001410442,0.0006774283,0.00007841105,0.0004607862,0.000006959269,0.0002013411,6.530921e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000006551834,"about_ca_system_score_gemma":0.00003392376,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004745197,"about_ca_topic_score_gemma":0.000008008791,"domain_scores_codex":[0.9988728,0.0001773612,0.0005759514,0.0001015097,0.0001793441,0.0000930094],"domain_scores_gemma":[0.9986057,0.0006583302,0.0003514937,0.00007639412,0.0002555294,0.00005257389],"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":[0.0003439007,0.0004190827,0.005013708,0.000005715709,0.0006005619,0.000001133097,0.0006760087,0.203445,0.001110318,0.2837337,0.00000778066,0.5046431],"study_design_scores_gemma":[0.00007187786,0.0002709779,0.003970621,0.0000190411,0.001845621,0.000001374071,0.0007588879,0.619585,0.001646062,0.3714418,0.0002807368,0.0001079601],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2497701,0.0001810794,0.7474868,0.001263572,0.00009397699,0.00005518903,0.000006595762,0.000003893034,0.001138808],"genre_scores_gemma":[0.9944849,0.000003052052,0.005210061,0.0000854642,0.0001977772,6.038649e-7,0.00001152768,0.000003665372,0.000002949889],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7447149,"threshold_uncertainty_score":0.2902505,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04537968571719844,"score_gpt":0.3891584714242128,"score_spread":0.3437787857070144,"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."}}