{"id":"W2004156982","doi":"10.3115/1119176.1119189","title":"Confidence estimation for translation prediction","year":2003,"lang":"en","type":"article","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":53,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"","keywords":"Correctness; Computer science; Perceptron; Artificial intelligence; Machine translation; Translation (biology); Machine learning; Context (archaeology); Artificial neural network; Estimation; Task (project management); Algorithm; 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":[0.01214755,0.001179131,0.001501198,0.00247422,0.0007460688,0.002539092,0.001712284,0.001969155,0.002612343],"category_scores_gemma":[0.1150809,0.0006117751,0.0008755052,0.001797931,0.001220106,0.005173289,0.002005173,0.00385968,0.001009286],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001188873,"about_ca_system_score_gemma":0.001095459,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003124884,"about_ca_topic_score_gemma":0.00221683,"domain_scores_codex":[0.9922725,0.004290854,0.0005111637,0.001013403,0.001584251,0.000327931],"domain_scores_gemma":[0.8870212,0.09758472,0.004763342,0.004236457,0.005772206,0.0006220819],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001492293,0.0001977715,0.0211356,0.0004982731,0.000404223,0.0002062994,0.0004983282,0.525589,0.007031356,0.02582307,0.003772029,0.4133519],"study_design_scores_gemma":[0.00002017248,0.00004226606,0.001160889,0.00002548716,0.00002724611,0.00006326037,0.00001932839,0.982264,0.003150465,0.01289233,0.000311033,0.00002349228],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05639526,0.0007637513,0.9380977,0.0006375368,0.00005998638,0.0000497012,0.0002278669,0.002301673,0.001466493],"genre_scores_gemma":[0.8795497,0.0002684052,0.118169,0.0001987791,0.0001227636,0.00007843044,0.0007494049,0.0002178856,0.0006455658],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01214755,"threshold_uncertainty_score":0.0642432,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02255088807747626,"score_gpt":0.2888816809473804,"score_spread":0.2663307928699041,"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."}}