{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002014533,0.00004402,0.00003915175,0.00004149289,0.0000570066,0.00007295679,0.0001441606,0.00003607711,0.000006112369],"category_scores_gemma":[0.00008597015,0.00003805245,0.0000181014,0.0001239469,0.000008261563,0.0006274562,0.000004624619,0.00003101958,0.000002963802],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001545997,"about_ca_system_score_gemma":0.00002362901,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003256637,"about_ca_topic_score_gemma":0.000001307038,"domain_scores_codex":[0.9995871,0.00001548513,0.00009270394,0.0001388399,0.00008824722,0.00007768817],"domain_scores_gemma":[0.9997047,0.00005429134,0.00003027951,0.0001313554,0.00006139766,0.00001797496],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.000001030972,0.000005875978,0.000007753293,0.000009476504,0.000001017951,1.276183e-7,0.0001073358,0.00003383853,0.002599141,0.9232957,0.0002692167,0.07366946],"study_design_scores_gemma":[0.0001103853,0.00003797131,0.00001135388,0.00001018726,0.000002145956,0.000007130282,0.000003261958,0.3567358,0.1251985,0.5168543,0.0009712426,0.00005775424],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00005619272,0.0002679482,0.997321,0.0002768042,0.00009310555,0.0001912743,7.462181e-7,0.0005818294,0.001211133],"genre_scores_gemma":[0.314061,0.000001387816,0.685749,0.00007688868,0.00000568846,0.00002195303,0.000002005455,0.000001882116,0.0000802169],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.4064414,"threshold_uncertainty_score":0.1551734,"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."}}