{"id":"W2185701500","doi":"10.1162/tacl_a_00239","title":"Measuring Machine Translation Errors in New Domains","year":2013,"lang":"en","type":"article","venue":"Transactions of the Association for Computational Linguistics","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":77,"is_retracted":false,"has_abstract":true,"ca_institutions":"National Research Council Canada","funders":"Defense Advanced Research Projects Agency; National Science Foundation","keywords":"Computer science; Machine translation; Natural language processing; Domain (mathematical analysis); Phrase; Machine translation software usability; Artificial intelligence; Evaluation of machine translation; Porting; Example-based machine translation; Rule-based machine translation; Translation (biology); Programming language","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":[0.009788002,0.0008871593,0.000966699,0.002999207,0.0008601692,0.002039157,0.0009784834,0.001367425,0.001199489],"category_scores_gemma":[0.0958329,0.0005322027,0.0005606752,0.003844236,0.001404963,0.004118084,0.002535453,0.00218275,0.0008006678],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009975034,"about_ca_system_score_gemma":0.0007121334,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002149454,"about_ca_topic_score_gemma":0.002159377,"domain_scores_codex":[0.9780115,0.009939123,0.002473002,0.002427395,0.006657641,0.0004914083],"domain_scores_gemma":[0.880864,0.0798969,0.01104394,0.008937624,0.01810442,0.001153129],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.002622331,0.001783848,0.2217986,0.001720604,0.001108728,0.0009711884,0.009714782,0.1574432,0.1490065,0.00530687,0.003571769,0.4449516],"study_design_scores_gemma":[0.0001830368,0.003114075,0.3306259,0.000182629,0.0004841894,0.001409266,0.004379227,0.3523328,0.2838315,0.01263303,0.01049017,0.0003341504],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9202732,0.0005929952,0.07176959,0.0003876248,0.0000814173,0.0002346296,0.0005695323,0.0007559647,0.005335064],"genre_scores_gemma":[0.936502,0.0002487844,0.05959171,0.0001785269,0.00006242957,0.0002757897,0.001298233,0.0003394027,0.00150309],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.009788002,"threshold_uncertainty_score":0.05176455,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02489167998879905,"score_gpt":0.2681288994135456,"score_spread":0.2432372194247465,"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."}}