{"id":"W4285105102","doi":"10.18653/v1/2022.acl-long.17","title":"CipherDAug: Ciphertext based Data Augmentation for Neural Machine Translation","year":2022,"lang":"en","type":"article","venue":"Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University","funders":"Natural Sciences and Engineering Research Council of Canada; Ministère de la Défense Nationale","keywords":"Computer science; Ciphertext; Machine translation; Plaintext; Artificial neural network; Leverage (statistics); Artificial intelligence; Source code; Transformer; Algorithm; Encryption; Programming language","routes":{"ca_aff":true,"ca_fund":true,"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":[0.001918341,0.000187393,0.0002560527,0.00009911703,0.0008241024,0.0001055973,0.002469451,0.00007304013,0.000003711248],"category_scores_gemma":[0.006013725,0.0001560196,0.0002167374,0.0005795778,0.00005228788,0.0002068916,0.0006450189,0.0002432679,2.029912e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002765018,"about_ca_system_score_gemma":0.0001635942,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003565116,"about_ca_topic_score_gemma":0.000007027915,"domain_scores_codex":[0.997595,0.0000518991,0.0006343651,0.0004234938,0.001026016,0.0002692539],"domain_scores_gemma":[0.9952158,0.0008840956,0.001740663,0.0002749817,0.00184572,0.00003870926],"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":[0.001292852,0.001403011,0.1226724,0.003072919,0.0009087688,7.229174e-7,0.009652964,0.6198499,0.01127806,0.1422768,0.03797701,0.04961453],"study_design_scores_gemma":[0.0009526339,0.0001449771,0.001997325,0.00008086598,0.0001261007,0.000001456053,0.0001318102,0.9717761,0.001838027,0.01852574,0.00419961,0.0002253802],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08228794,0.007949923,0.7754119,0.05492772,0.02242122,0.02315226,0.02194444,0.002977858,0.008926741],"genre_scores_gemma":[0.8121439,5.048626e-7,0.1868518,0.000341236,0.0001591069,0.00007231022,0.0001448515,0.00002471159,0.0002615677],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.729856,"threshold_uncertainty_score":0.7199425,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01925407382792177,"score_gpt":0.2733220621644697,"score_spread":0.2540679883365479,"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."}}