{"id":"W2132891320","doi":"10.1007/s10590-011-9112-y","title":"Improved Arabic-to-English statistical machine translation by reordering post-verbal subjects for word alignment","year":2011,"lang":"en","type":"article","venue":"Machine Translation","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":44,"is_retracted":false,"has_abstract":false,"ca_institutions":"National Research Council Canada","funders":"University of Pennsylvania","keywords":"Computer science; Machine translation; Natural language processing; Word order; Artificial intelligence; Phrase; Parsing; Word (group theory); Translation (biology); Speech recognition; Arabic; Computational linguistics; Linguistics","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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004765555,0.0002877464,0.0002487106,0.0001656316,0.0001664107,0.0001350562,0.00054152,0.0001276194,0.00003159053],"category_scores_gemma":[0.00007625814,0.0002706739,0.00008357627,0.0003332316,0.00002878318,0.000749474,0.00003523957,0.000223464,0.000003396432],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006485869,"about_ca_system_score_gemma":0.0000349769,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003580445,"about_ca_topic_score_gemma":0.0002141948,"domain_scores_codex":[0.9981636,0.00008320974,0.0004339871,0.0005999027,0.0003123508,0.0004069161],"domain_scores_gemma":[0.9990577,0.0001486651,0.0001084565,0.0003689289,0.0001648787,0.0001513723],"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":[0.000337912,0.0001449155,0.00009739576,0.0001061236,0.00002784909,0.000004907332,0.008171529,0.00001683415,0.03843059,0.004755332,0.0001564866,0.9477502],"study_design_scores_gemma":[0.003297725,0.001399355,0.0008617472,0.0001206912,0.0001079379,0.00001832396,0.0000506148,0.8710948,0.09379132,0.02445987,0.003411572,0.001386056],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00209775,0.00199661,0.9927237,0.0006624181,0.0002531485,0.001026725,0.0001701017,0.000815897,0.0002536541],"genre_scores_gemma":[0.5430635,0.000005170642,0.4564219,0.0001922102,0.00003789654,0.0000703718,0.0001661323,0.00002332578,0.00001950168],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.946364,"threshold_uncertainty_score":0.9999745,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01793620875493665,"score_gpt":0.2589407352169916,"score_spread":0.241004526462055,"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."}}