{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002791682,0.0009147387,0.0008267062,0.0007900003,0.0007157268,0.001173315,0.0009687907,0.0009628485,0.001596352],"category_scores_gemma":[0.01426862,0.0003651365,0.0004375807,0.0007266786,0.0005660243,0.001344587,0.001281256,0.0009268823,0.0009601091],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001095039,"about_ca_system_score_gemma":0.0009372423,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002146474,"about_ca_topic_score_gemma":0.004894118,"domain_scores_codex":[0.9972487,0.001207762,0.000270951,0.0005710367,0.0005335929,0.0001679475],"domain_scores_gemma":[0.9952198,0.002512294,0.0002680484,0.000829082,0.00102881,0.0001420539],"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":[0.001579655,0.0004437978,0.01713818,0.001151003,0.00036545,0.000591615,0.000580329,0.2911146,0.1522488,0.007993255,0.01165051,0.5151429],"study_design_scores_gemma":[0.0001128991,0.0007479161,0.008663564,0.00005780492,0.0001796346,0.000511627,0.0001776041,0.7920763,0.1799973,0.006722424,0.01064147,0.000111464],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6110138,0.003095608,0.3455554,0.0006014343,0.0003851089,0.0002586483,0.0008808554,0.02151028,0.01669897],"genre_scores_gemma":[0.8958253,0.0001569762,0.09950335,0.0001620549,0.00004205489,0.0001075437,0.00132277,0.0005735575,0.002306439],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.002791682,"threshold_uncertainty_score":0.01476401,"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."}}