{"id":"W4385571651","doi":"10.18653/v1/2023.findings-acl.597","title":"Leveraging Synthetic Targets for Machine Translation","year":2023,"lang":"en","type":"article","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"","keywords":"Computer science; Machine translation; Ground truth; Translation (biology); Synthetic data; Training set; Artificial intelligence; Machine learning; Natural language processing","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":[0.004175521,0.001691273,0.001077792,0.0008871073,0.0008229669,0.001811677,0.001856124,0.001622509,0.004335271],"category_scores_gemma":[0.01928459,0.000691939,0.0009600152,0.001538884,0.001095689,0.003125434,0.002478945,0.002325179,0.003790093],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000755761,"about_ca_system_score_gemma":0.0009891032,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002971037,"about_ca_topic_score_gemma":0.00404297,"domain_scores_codex":[0.9964036,0.002212688,0.0001758928,0.0005870284,0.0004777776,0.0001431119],"domain_scores_gemma":[0.9913501,0.005269812,0.0003082892,0.001807717,0.001078312,0.0001857971],"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":[0.001536226,0.000682631,0.008287156,0.0010699,0.0003900591,0.0008072245,0.0006786494,0.736239,0.02880534,0.02162801,0.03040086,0.1694749],"study_design_scores_gemma":[0.00009288867,0.0003024231,0.001266798,0.00008009932,0.00006441049,0.0003908153,0.0001987033,0.9342528,0.02667701,0.02101923,0.01559818,0.00005669837],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2035836,0.001429672,0.7628376,0.001644018,0.0007576568,0.0004434737,0.007178337,0.0093553,0.01277034],"genre_scores_gemma":[0.7759891,0.0005336837,0.1839423,0.0006582031,0.0002143803,0.0008375773,0.03161454,0.001498253,0.004712021],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004335271,"threshold_uncertainty_score":0.02208251,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02886372056259232,"score_gpt":0.2904904127056248,"score_spread":0.2616266921430324,"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."}}