{"id":"W2971045947","doi":"10.18653/v1/w19-5434","title":"NRC Parallel Corpus Filtering System for WMT 2019","year":2019,"lang":"en","type":"article","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Computer science; Task (project management); Machine translation; Natural language processing; Artificial intelligence; Translation (biology); Information retrieval; Engineering","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002627638,0.0001093398,0.0001467609,0.00006188302,0.00004856668,0.0001728864,0.0008969395,0.00006216368,0.00001145633],"category_scores_gemma":[0.00002388816,0.00008510424,0.00005601536,0.0001239293,0.00000834436,0.0004204141,0.0002385559,0.00007241096,0.0001282402],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007761658,"about_ca_system_score_gemma":0.0000385542,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004228479,"about_ca_topic_score_gemma":0.000002775112,"domain_scores_codex":[0.9990806,0.0000134594,0.0001516353,0.0003095901,0.0002082552,0.0002364883],"domain_scores_gemma":[0.9991986,0.00006749447,0.00007012123,0.0004942769,0.0001245598,0.00004494338],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00002308416,0.00002793497,0.0002442497,0.0005308178,0.00002255372,0.00001406016,0.000249733,0.00004050002,0.04661408,0.8743485,0.02071022,0.05717425],"study_design_scores_gemma":[0.002528396,0.000808485,0.0002293524,0.000930357,0.00002479046,0.0003503627,0.0001390411,0.4030058,0.4755105,0.05237854,0.06203475,0.002059583],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00119822,0.0007313369,0.9919397,0.0002484142,0.0004780969,0.0003854405,0.00000217773,0.001476995,0.003539642],"genre_scores_gemma":[0.276076,0.000002007456,0.7198876,0.0001727535,0.0000377921,0.00002667713,0.000001638674,0.000009131349,0.003786387],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.82197,"threshold_uncertainty_score":0.347045,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0106279065497854,"score_gpt":0.2485762465397344,"score_spread":0.237948339989949,"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."}}