{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01773942,0.001595785,0.001919982,0.006614158,0.001150668,0.003867452,0.002389209,0.002545687,0.002923929],"category_scores_gemma":[0.1817769,0.0008163168,0.001477259,0.004514826,0.00246889,0.007057548,0.002816643,0.003084298,0.001177663],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001591202,"about_ca_system_score_gemma":0.00120533,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001484701,"about_ca_topic_score_gemma":0.0007071667,"domain_scores_codex":[0.977032,0.01073644,0.001773375,0.002266762,0.007690343,0.0005010507],"domain_scores_gemma":[0.8278335,0.148691,0.007185244,0.006669271,0.00886376,0.0007571947],"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":[0.0009358517,0.0001472514,0.0153935,0.001005812,0.0007096624,0.000217643,0.0005819143,0.3288257,0.006068152,0.08984554,0.004041324,0.5522277],"study_design_scores_gemma":[0.00006224454,0.0001845964,0.003489918,0.0001407945,0.0001062863,0.0003692496,0.00008343089,0.8641735,0.008650952,0.1194004,0.003195381,0.0001432281],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01313833,0.001886627,0.9822025,0.0001925404,0.00006287755,0.00005381737,0.0001450533,0.0008574763,0.001460856],"genre_scores_gemma":[0.4547023,0.0008907576,0.5411777,0.0001809682,0.0003304452,0.000307122,0.001083403,0.0005740719,0.0007533101],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01773942,"threshold_uncertainty_score":0.0938161,"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."}}