{"id":"W3198097706","doi":"","title":"Like Chalk and Cheese? On the Effects of Translationese in MT Training","year":2021,"lang":"en","type":"article","venue":"NPARC","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Translation (biology); Training (meteorology); Computer science; Training set; Machine translation; Quality (philosophy); Artificial intelligence; Matching (statistics); Natural language processing; Machine learning; Mathematics; Statistics; Geography","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":true,"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":[0.01477402,0.001188212,0.0007293441,0.000961834,0.001550535,0.002178294,0.000776182,0.001797437,0.002870976],"category_scores_gemma":[0.06323505,0.0003866077,0.0004686373,0.001133003,0.001722179,0.003433358,0.002201357,0.002599442,0.001542842],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001063182,"about_ca_system_score_gemma":0.0009897004,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009754391,"about_ca_topic_score_gemma":0.0210137,"domain_scores_codex":[0.9902829,0.007087164,0.0004771365,0.001154984,0.0007474764,0.0002503388],"domain_scores_gemma":[0.926897,0.06231076,0.002010812,0.0047284,0.003121085,0.0009319554],"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":[0.006423608,0.001094848,0.0966262,0.00115714,0.0009899919,0.0006217054,0.002031296,0.1604831,0.02945734,0.00583178,0.02059373,0.6746892],"study_design_scores_gemma":[0.0005742025,0.004750503,0.09067219,0.0008032775,0.0008749265,0.001169407,0.002191544,0.761952,0.08859598,0.02209966,0.02606781,0.000248557],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8955435,0.014124,0.06039822,0.004603821,0.0006435993,0.0001533895,0.001381658,0.002367654,0.02078409],"genre_scores_gemma":[0.9633909,0.0009082777,0.02868251,0.0007756888,0.0002147061,0.00005586366,0.002358202,0.0004766964,0.003137151],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01477402,"threshold_uncertainty_score":0.07813346,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0143069889104044,"score_gpt":0.249714511052249,"score_spread":0.2354075221418445,"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."}}