{"id":"W2144746247","doi":"10.3115/1220355.1220401","title":"Confidence estimation for machine translation","year":2004,"lang":"en","type":"article","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":356,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"","keywords":"NIST; Correctness; Computer science; Machine translation; Natural language processing; Context (archaeology); Artificial intelligence; Translation (biology); Estimation; Evaluation of machine translation; Machine learning; Machine translation software usability; Example-based machine translation; 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":[0.0001088459,0.00004734179,0.00004443393,0.00003966638,0.00004887105,0.00007367315,0.0002610029,0.00002811971,0.000003174646],"category_scores_gemma":[0.00003234535,0.00003861675,0.00001976829,0.0001127597,0.000009716458,0.0005251555,0.00001419942,0.00003392669,0.000004739137],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002103739,"about_ca_system_score_gemma":0.00002639485,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004018379,"about_ca_topic_score_gemma":0.00001226277,"domain_scores_codex":[0.9996167,0.000004251599,0.00008347784,0.0001319026,0.0000845628,0.00007914317],"domain_scores_gemma":[0.9997387,0.0000339834,0.00002811622,0.000136503,0.00004400426,0.00001869881],"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":[0.000001836597,0.000007591484,0.000001170333,0.00001048995,9.221537e-7,5.066653e-7,0.0001605052,0.0001616137,0.002457157,0.798916,0.00002697849,0.1982552],"study_design_scores_gemma":[0.0001744166,0.00003357645,0.000005801171,0.00001345969,0.00000134404,0.000006256897,0.000001006504,0.2103886,0.09415485,0.6950628,0.00009570091,0.00006216524],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00005899476,0.0006438774,0.9957084,0.002525911,0.00004156565,0.0001637337,6.871999e-7,0.0005931266,0.0002637129],"genre_scores_gemma":[0.4004314,0.000001075871,0.5993389,0.0001832736,0.000005900533,0.00001052829,0.000002366452,0.00000174569,0.00002474741],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.4003724,"threshold_uncertainty_score":0.1574745,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01942382530659272,"score_gpt":0.3005074643097555,"score_spread":0.2810836390031628,"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."}}