{"id":"W2896826757","doi":"10.1007/s10579-018-9430-2","title":"VERTa: a linguistic approach to automatic machine translation evaluation","year":2018,"lang":"en","type":"article","venue":"Language Resources and Evaluation","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":false,"ca_institutions":"","funders":"Ministerio de Asuntos Económicos y Transformación Digital, Gobierno de España; Alberta-Pacific Forest Industries","keywords":"Metric (unit); Computer science; Machine translation; Natural language processing; Variety (cybernetics); Artificial intelligence; Linguistics; Engineering","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01327602,0.002232209,0.00212241,0.008677003,0.00236463,0.006756734,0.003678476,0.002317897,0.01080819],"category_scores_gemma":[0.03083114,0.001215867,0.00154607,0.004650963,0.001393766,0.006629603,0.005087656,0.002953477,0.00554728],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001554767,"about_ca_system_score_gemma":0.003558728,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004772209,"about_ca_topic_score_gemma":0.008031053,"domain_scores_codex":[0.968594,0.02035155,0.002028133,0.001913364,0.006417021,0.0006959033],"domain_scores_gemma":[0.9791027,0.009897619,0.0007605152,0.003166916,0.00660485,0.0004674677],"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":[0.001363081,0.001032446,0.002972124,0.001997556,0.0009867551,0.0004803512,0.001155837,0.0178584,0.04439858,0.04210081,0.1049659,0.7806882],"study_design_scores_gemma":[0.0006484146,0.001183056,0.003998065,0.000476478,0.0007216603,0.001056969,0.001118432,0.7118655,0.08275644,0.07799259,0.1177626,0.0004198474],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0222511,0.001412153,0.8927895,0.0006326675,0.0006652174,0.001506054,0.00542806,0.05830555,0.0170097],"genre_scores_gemma":[0.1394438,0.0006178573,0.8248838,0.0004997357,0.000318033,0.00167253,0.01448422,0.007433807,0.01064623],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01327602,"threshold_uncertainty_score":0.07021117,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03038743013763573,"score_gpt":0.3296793279805589,"score_spread":0.2992918978429232,"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."}}