{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002902656,0.00009296014,0.0001298541,0.0001376058,0.0001304476,0.00005985178,0.0004437771,0.00007732515,0.000005660943],"category_scores_gemma":[0.0005983054,0.00008207193,0.0001101756,0.0004354404,0.00001417735,0.000148804,0.00001070902,0.000153042,0.000003032959],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002070497,"about_ca_system_score_gemma":0.0001655301,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002539495,"about_ca_topic_score_gemma":0.0001051865,"domain_scores_codex":[0.9989555,0.00004755844,0.0003450801,0.000152819,0.0003541507,0.0001448285],"domain_scores_gemma":[0.9985641,0.00046169,0.0002602707,0.0001540034,0.0005262165,0.00003371488],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00003642566,0.0004440085,0.008568615,0.0002013625,0.00019926,6.153313e-7,0.003468418,0.5390531,0.001076243,0.3646112,0.001339159,0.08100156],"study_design_scores_gemma":[0.0007418247,0.00003569429,0.004412647,0.00005691333,0.00002819549,0.000001205751,0.00001234447,0.5488575,0.002077811,0.4425853,0.001014518,0.000176054],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0004474765,0.0001907287,0.9968857,0.001258779,0.0003947939,0.0003927506,0.00001834161,0.0001121558,0.0002992704],"genre_scores_gemma":[0.5807684,0.000001348525,0.4189285,0.00004525401,0.00003708514,0.00001179108,0.000006223426,0.000005908427,0.0001955121],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.580321,"threshold_uncertainty_score":0.3346796,"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."}}