{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00486376,0.0003684484,0.0006066866,0.002959391,0.0008985989,0.003278647,0.0004603377,0.0007479464,0.002682977],"category_scores_gemma":[0.01867468,0.0001833446,0.0002930729,0.002809058,0.003564146,0.003750035,0.001592248,0.001740747,0.0004213634],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009523283,"about_ca_system_score_gemma":0.0005157721,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001183395,"about_ca_topic_score_gemma":0.002042489,"domain_scores_codex":[0.996273,0.002330605,0.000156055,0.0004869862,0.0006082986,0.0001449911],"domain_scores_gemma":[0.9837124,0.01282236,0.001146975,0.0009854997,0.0009758917,0.0003568158],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.002960713,0.0003920102,0.1973631,0.001280062,0.0009728507,0.002259983,0.02738713,0.01921145,0.1590488,0.2539157,0.006001375,0.3292069],"study_design_scores_gemma":[0.0001295136,0.0009818107,0.4808874,0.0003692632,0.0003854569,0.00267598,0.01850969,0.06027025,0.0351783,0.3768546,0.02352371,0.0002340234],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9199578,0.004843834,0.0498286,0.003851873,0.00008855452,0.00003456031,0.0005873243,0.0002292325,0.02057835],"genre_scores_gemma":[0.9933867,0.0003315083,0.005630956,0.0001780343,0.0000367843,0.0000108734,0.0001585995,0.0000646499,0.0002018292],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.00486376,"threshold_uncertainty_score":0.02572232,"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."}}