{"id":"W7135940324","doi":"","title":"LEPOR:An Augmented Machine Translation Evaluation Metric - MT Evaluation, Quality Estimation, and Multilingual Treebanks","year":2017,"lang":"en","type":"book","venue":"Research Explorer (The University of Manchester)","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"Open Text (Canada)","funders":"","keywords":"Machine translation; Metric (unit); Quality (philosophy); Translation (biology); Quality assessment","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":[0.006778965,0.002500345,0.002525639,0.006777453,0.001246572,0.004593833,0.002891274,0.001836151,0.01206548],"category_scores_gemma":[0.0182072,0.0008647142,0.001311583,0.006420682,0.000816842,0.007364337,0.004492121,0.002053226,0.008075231],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001807541,"about_ca_system_score_gemma":0.002041345,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002747015,"about_ca_topic_score_gemma":0.004919744,"domain_scores_codex":[0.9885409,0.003593088,0.0009361114,0.001168002,0.005447739,0.0003140234],"domain_scores_gemma":[0.9907368,0.002989508,0.0005660549,0.001846699,0.00356789,0.0002931326],"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":[0.0003099222,0.0001017384,0.001070083,0.0009619194,0.0001909026,0.0001378896,0.0002006682,0.01054879,0.01066991,0.01979165,0.09413528,0.8618814],"study_design_scores_gemma":[0.000236282,0.0009536924,0.008479198,0.0009273445,0.0004509113,0.002161166,0.0002857542,0.4771857,0.05683527,0.08970717,0.3623944,0.000383151],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01452418,0.008416149,0.8936912,0.0008242499,0.0009897085,0.0004973834,0.009016526,0.04581964,0.02622106],"genre_scores_gemma":[0.09896521,0.002426423,0.8338664,0.0004288122,0.0004173715,0.0008129759,0.02771345,0.008362554,0.02700691],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01206548,"threshold_uncertainty_score":0.04036301,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2214088008740083,"score_gpt":0.4251339928660098,"score_spread":0.2037251919920015,"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."}}