{"id":"W2111856253","doi":"10.1162/coli.2007.33.1.9","title":"Word-Level Confidence Estimation for Machine Translation","year":2007,"lang":"en","type":"article","venue":"Computational Linguistics","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":106,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Research Council Canada; RWTH Aachen University; European Commission","keywords":"Computer science; Word (group theory); Phrase; Machine translation; Translation (biology); Natural language processing; Artificial intelligence; Example-based machine translation; Linguistics","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005494632,0.0001153809,0.0001075705,0.0001320301,0.0001523959,0.0001143301,0.0003929661,0.00006669373,0.000002449378],"category_scores_gemma":[0.001617474,0.0001182538,0.00004288153,0.0002469255,0.00003672504,0.000100047,0.00003854632,0.0001079287,0.000006190433],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004910169,"about_ca_system_score_gemma":0.00008798507,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000794121,"about_ca_topic_score_gemma":0.000006598346,"domain_scores_codex":[0.9989657,0.00001337215,0.0003022729,0.0002480218,0.0002833989,0.0001871712],"domain_scores_gemma":[0.9980484,0.0008718428,0.000133166,0.000155369,0.0007313395,0.00005987742],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001566753,0.00002816488,0.00003019,0.00003986647,0.000006456799,0.000005545327,0.0002244146,0.00780508,0.00005665724,0.7838953,0.0002586815,0.207634],"study_design_scores_gemma":[0.0001464974,0.00002286441,0.0001820774,0.00002225256,0.000004577546,0.000005333006,0.00000149025,0.5880851,0.0007840906,0.4094072,0.001235348,0.0001031629],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00004404034,0.0007700111,0.9974925,0.0002064104,0.0004745378,0.0002246124,0.00002186103,0.0003890236,0.0003770116],"genre_scores_gemma":[0.4207276,6.866873e-7,0.5788585,0.0001720817,0.0001391661,0.000004504883,0.00006659253,0.000006407751,0.00002448112],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.5802801,"threshold_uncertainty_score":0.4822249,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04620772119004527,"score_gpt":0.3427001006526349,"score_spread":0.2964923794625896,"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."}}