{"id":"W1972788481","doi":"10.3115/1599081.1599196","title":"Tighter integration of rule-based and statistical MT in serial system combination","year":2008,"lang":"en","type":"article","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"ca_institutions":"National Research Council Canada","funders":"","keywords":"Computer science; Machine translation; NIST; Task (project management); Natural language processing; Phrase; Language model; Artificial intelligence","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":[0.01270168,0.001820619,0.002647646,0.003655811,0.0009123769,0.003378309,0.002427052,0.001607588,0.003356253],"category_scores_gemma":[0.0322777,0.002000798,0.001047202,0.00371232,0.001392401,0.005728027,0.004868894,0.00265419,0.003020593],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008971667,"about_ca_system_score_gemma":0.001840804,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004429795,"about_ca_topic_score_gemma":0.007069145,"domain_scores_codex":[0.9803051,0.008528123,0.0019838,0.003185648,0.005492895,0.0005044279],"domain_scores_gemma":[0.9699264,0.01090113,0.001676167,0.01113693,0.005954088,0.000405334],"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":[0.000661339,0.0008175365,0.007003906,0.000443317,0.0005530776,0.0005546429,0.0009617265,0.08503534,0.08821434,0.005618179,0.003751497,0.806385],"study_design_scores_gemma":[0.0002003239,0.0009997207,0.008935238,0.0001068047,0.000548804,0.001122958,0.0002832968,0.8734555,0.07660519,0.01839011,0.01914725,0.0002048569],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06676373,0.0008698109,0.9146625,0.0003051455,0.00009587243,0.000399633,0.0001234433,0.01024537,0.006534447],"genre_scores_gemma":[0.3624028,0.0003267589,0.6293037,0.0005087316,0.0001521877,0.0003288641,0.0008963193,0.001599951,0.004480714],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01270168,"threshold_uncertainty_score":0.06717366,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01236545472704667,"score_gpt":0.2523569544143908,"score_spread":0.2399914996873441,"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."}}