{"id":"W4394773742","doi":"10.1162/tacl_a_00645","title":"To Diverge or Not to Diverge: A Morphosyntactic Perspective on Machine Translation vs Human Translation","year":2024,"lang":"en","type":"article","venue":"Transactions of the Association for Computational Linguistics","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"Google (Canada)","funders":"","keywords":"Divergence (linguistics); Machine translation; Perspective (graphical); Computer science; Translation (biology); Artificial intelligence; Natural language processing; Diversity (politics); Linguistics; Sociology; Biology","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":[0.0004267047,0.0001859978,0.0002058206,0.0003467929,0.0004231673,0.0001774035,0.000535742,0.0001053777,0.00001407685],"category_scores_gemma":[0.0007301071,0.0001528258,0.0002097025,0.0009742859,0.00001675594,0.0001532413,0.00001914873,0.0002399644,0.00001373078],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007004217,"about_ca_system_score_gemma":0.0001479669,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001158343,"about_ca_topic_score_gemma":0.00008433926,"domain_scores_codex":[0.9982452,0.00007789834,0.0003969655,0.000389787,0.0006841073,0.0002060445],"domain_scores_gemma":[0.997525,0.001093367,0.0001554464,0.0002283438,0.0009220597,0.00007581787],"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":[0.0007681038,0.0005528358,0.0001030638,0.0003328595,0.0005185981,0.000005541683,0.01427238,0.2984111,0.002780545,0.6481219,0.001883223,0.03224983],"study_design_scores_gemma":[0.001481306,0.00165415,0.002512637,0.0006220755,0.0005094534,0.000007981934,0.0001508632,0.7603824,0.01756227,0.2008457,0.01323232,0.001038786],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0005004664,0.0001016643,0.9908423,0.005623654,0.001068826,0.00079929,0.0004276235,0.0003708641,0.0002653498],"genre_scores_gemma":[0.7763106,0.000001794819,0.2227133,0.0003407014,0.0001267289,0.00004115572,0.00002524285,0.00001989793,0.0004205457],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7758102,"threshold_uncertainty_score":0.6232057,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0292461547114884,"score_gpt":0.3409946650393249,"score_spread":0.3117485103278365,"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."}}