{"id":"W2973276266","doi":"10.48550/arxiv.1909.09268","title":"Towards Neural Language Evaluators","year":2019,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Topic Modeling","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université Laval","funders":"","keywords":"Computer science; Metric (unit); Natural language processing; Transformer; Artificial intelligence; BLEU; Machine learning; Information retrieval; Machine translation; Engineering","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":[0.01937793,0.001694744,0.001627114,0.004173669,0.0009572037,0.005538515,0.002924704,0.002440328,0.006343194],"category_scores_gemma":[0.08601128,0.0006034864,0.0007654955,0.002280125,0.001570144,0.01067559,0.003563598,0.00509976,0.005276158],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002704799,"about_ca_system_score_gemma":0.002111427,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00288607,"about_ca_topic_score_gemma":0.004791728,"domain_scores_codex":[0.9852775,0.008820378,0.0007280151,0.00223372,0.002479268,0.0004612611],"domain_scores_gemma":[0.9558704,0.02753542,0.001712881,0.003802532,0.009903014,0.001175678],"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":[0.0005040371,0.0002575799,0.005777334,0.0009250586,0.0002633281,0.0000935048,0.0007534334,0.04450248,0.006376942,0.04925478,0.04047156,0.8508199],"study_design_scores_gemma":[0.00007860359,0.0004008498,0.002180739,0.0006861507,0.0001673664,0.0001682998,0.0004990713,0.7662636,0.01372794,0.1778734,0.03784194,0.0001119956],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02476001,0.01311855,0.9276735,0.006964563,0.0006648533,0.0002367483,0.001486773,0.00953584,0.01555921],"genre_scores_gemma":[0.4813509,0.004133448,0.4855631,0.003453168,0.001375826,0.0008295402,0.004946288,0.001422758,0.01692494],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01937793,"threshold_uncertainty_score":0.1024815,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08674456871558647,"score_gpt":0.211965579487791,"score_spread":0.1252210107722045,"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."}}