{"id":"W4400655051","doi":"10.5267/j.ijdns.2024.5.009","title":"Assessing the accuracy of MT and AI tools in translating humanities or social sciences Arabic research titles into English: Evidence from Google Translate, Gemini, and ChatGPT","year":2024,"lang":"en","type":"article","venue":"International Journal of Data and Network Science","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Diction; Arabic; Computer science; Natural language processing; Linguistics; Syntax; Equivalence (formal languages); Artificial intelligence; Philosophy","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":[0.05068921,0.0009447576,0.0009001563,0.0061093,0.001987861,0.005272991,0.001556181,0.001717906,0.002000249],"category_scores_gemma":[0.2797272,0.0004975862,0.0008205477,0.007924259,0.003385071,0.008398765,0.003421686,0.001615647,0.002367197],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001351149,"about_ca_system_score_gemma":0.002372094,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007619277,"about_ca_topic_score_gemma":0.007689994,"domain_scores_codex":[0.9548367,0.0257288,0.005504814,0.00325054,0.009939056,0.0007401733],"domain_scores_gemma":[0.6264738,0.2656928,0.03264293,0.02055323,0.05217064,0.002466567],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.004550073,0.001165538,0.4322749,0.008160282,0.0009320286,0.001706416,0.1074852,0.003249806,0.006237314,0.004242329,0.007009085,0.422987],"study_design_scores_gemma":[0.0005759982,0.005729447,0.741522,0.007051697,0.00267285,0.005496575,0.08966044,0.02938296,0.03159497,0.007465648,0.07824175,0.0006056204],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9659149,0.005140601,0.005804463,0.001659876,0.0002198704,0.0003343892,0.001199109,0.0001794571,0.01954738],"genre_scores_gemma":[0.9812192,0.003026439,0.01163749,0.000531514,0.0001535349,0.0001747061,0.001674738,0.0001591103,0.001423234],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.05068921,"threshold_uncertainty_score":0.2680733,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2388636457454777,"score_gpt":0.4978445780223662,"score_spread":0.2589809322768886,"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."}}