{"id":"W2250257730","doi":"10.18653/v1/w15-3056","title":"Improving evaluation and optimization of MT systems against MEANT","year":2015,"lang":"en","type":"article","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"National Research Council Canada","funders":"Advanced Research Projects Agency; Defense Advanced Research Projects Agency; European Commission","keywords":"Computer science","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":[],"consensus_categories":[],"category_scores_codex":[0.0007950705,0.00004712418,0.00006946712,0.0000640197,0.00001917449,0.00008484959,0.0001807935,0.00002173195,5.705819e-7],"category_scores_gemma":[0.0001787026,0.00003628678,0.00000711413,0.000141172,0.00001298319,0.0004505193,0.0001028114,0.0000312887,4.060131e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003721975,"about_ca_system_score_gemma":0.00006905403,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007846564,"about_ca_topic_score_gemma":0.000001581324,"domain_scores_codex":[0.9993616,0.00004723553,0.0001268034,0.0001343022,0.0002664951,0.00006360954],"domain_scores_gemma":[0.9993237,0.00001578296,0.00009605553,0.0001668244,0.0003616453,0.00003596443],"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":[0.00001875806,0.0001304317,0.0004346975,0.0003833426,0.0000306893,0.00001141176,0.003392818,0.1291413,0.03313015,0.1463559,0.001374187,0.6855963],"study_design_scores_gemma":[0.0001145493,0.00003203734,0.000001741301,0.00002282731,0.00000319714,0.000005657036,0.0000401573,0.9913043,0.007447914,0.0009707077,0.000007484971,0.00004936813],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001862593,0.002218305,0.9946638,0.00006223155,0.00009444779,0.0001604138,2.009755e-7,0.0001865571,0.0007514295],"genre_scores_gemma":[0.5000829,0.000003151395,0.4998575,0.00002005596,0.000008828472,0.00000463716,0.000001132663,0.000001984608,0.00001985853],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8621631,"threshold_uncertainty_score":0.1479732,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02890033713408698,"score_gpt":0.2865654101048546,"score_spread":0.2576650729707677,"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."}}