{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0170647,0.00157136,0.0027111,0.006036328,0.001360917,0.004188172,0.002940698,0.00282462,0.004034267],"category_scores_gemma":[0.204687,0.001125797,0.001831429,0.005621516,0.003084331,0.007656869,0.003694483,0.004639934,0.001465323],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00171344,"about_ca_system_score_gemma":0.001180665,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002006905,"about_ca_topic_score_gemma":0.0007858269,"domain_scores_codex":[0.976604,0.01199164,0.001732993,0.002758735,0.006127637,0.0007848838],"domain_scores_gemma":[0.7571788,0.2105353,0.009310734,0.01116813,0.01081116,0.0009960175],"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":[0.0007985792,0.000125007,0.01388713,0.001195285,0.000549535,0.0004198067,0.0005801775,0.3181071,0.0064823,0.2020416,0.007513291,0.4483002],"study_design_scores_gemma":[0.0000366666,0.0001129098,0.002133299,0.0001289275,0.00007521416,0.000362041,0.00004379052,0.8140833,0.005487905,0.1745016,0.002945393,0.0000889362],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.008382616,0.002572977,0.9865919,0.0003575102,0.00007392007,0.0000378062,0.0001631309,0.000537347,0.001282783],"genre_scores_gemma":[0.5637931,0.002450346,0.4279362,0.0003352048,0.001046551,0.0002709323,0.001936212,0.0006121898,0.001619252],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.0170647,"threshold_uncertainty_score":0.09024787,"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."}}