{"id":"W3023412526","doi":"10.5539/ijel.v10n4p43","title":"Neural Machine Translation: Fine-Grained Evaluation of Google Translate Output for English-to-Arabic Translation","year":2020,"lang":"en","type":"article","venue":"International Journal of English Linguistics","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Machine translation; Fluency; Computer science; Evaluation of machine translation; Natural language processing; Sentence; Quality (philosophy); Machine translation software usability; Artificial intelligence; Readability; Translation (biology); Arabic; Point (geometry); Example-based machine translation; Linguistics; Mathematics","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00420666,0.001277682,0.0009122351,0.002200585,0.0007917873,0.001301041,0.0009179359,0.0009786674,0.002947921],"category_scores_gemma":[0.01775753,0.0002124925,0.0005629905,0.001961246,0.0006783482,0.001564341,0.001124276,0.0005327709,0.001660813],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001048261,"about_ca_system_score_gemma":0.000910609,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01167323,"about_ca_topic_score_gemma":0.01252633,"domain_scores_codex":[0.9953935,0.002083638,0.0006388607,0.0004960311,0.001198369,0.0001896265],"domain_scores_gemma":[0.9912548,0.00378612,0.0003878486,0.0007536492,0.003557419,0.0002601749],"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":[0.01104266,0.002999997,0.03149891,0.005825513,0.0009817081,0.002900998,0.004474583,0.09619575,0.07747822,0.003249304,0.04459681,0.7187556],"study_design_scores_gemma":[0.001271044,0.00531714,0.08972216,0.0002847183,0.0005840551,0.001840778,0.002978819,0.7636133,0.1062562,0.002905813,0.024911,0.0003150786],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9498222,0.001446963,0.0238914,0.0003057907,0.0003681747,0.0008274266,0.003930775,0.008365332,0.01104194],"genre_scores_gemma":[0.9392213,0.0003914608,0.0432356,0.0001170029,0.00006326299,0.0003916333,0.01209647,0.0005681437,0.003914991],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01167323,"threshold_uncertainty_score":0.02321059,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05410833016145049,"score_gpt":0.3399550057378458,"score_spread":0.2858466755763953,"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."}}