{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001236823,0.002108404,0.001146742,0.001704387,0.001123745,0.001994831,0.0008943033,0.0006976207,0.01394494],"category_scores_gemma":[0.005473094,0.0005519444,0.0009084572,0.00218349,0.0003872928,0.001600948,0.001227295,0.00181887,0.01604931],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004973943,"about_ca_system_score_gemma":0.002425225,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003656298,"about_ca_topic_score_gemma":0.007369354,"domain_scores_codex":[0.9983451,0.0006425359,0.0002477737,0.0003583229,0.000288697,0.0001174746],"domain_scores_gemma":[0.9949585,0.00133548,0.0002078441,0.0009093176,0.002481417,0.0001075901],"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":[0.0008858418,0.0004157586,0.001275812,0.0008385934,0.0001782206,0.0007709028,0.0008544646,0.01141351,0.1349755,0.01323057,0.03786577,0.797295],"study_design_scores_gemma":[0.0003638729,0.0008872119,0.004217635,0.0001828245,0.0005208398,0.001544462,0.001192793,0.4632554,0.3407238,0.0264083,0.1603683,0.0003344363],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03865902,0.0008216235,0.9219839,0.0006267181,0.001312724,0.0003420261,0.003296159,0.02462273,0.008335003],"genre_scores_gemma":[0.1260379,0.0005232043,0.8511017,0.0002242226,0.0003180604,0.0002606301,0.008393636,0.003933043,0.009207746],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01394494,"threshold_uncertainty_score":0.04665053,"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."}}