{"id":"W3206689743","doi":"10.1609/aaai.v36i10.21323","title":"Non-autoregressive Translation with Layer-Wise Prediction and Deep Supervision","year":2022,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":24,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"DeepMind; Compute Canada; Natural Sciences and Engineering Research Council of Canada; Canadian Institute for Advanced Research","keywords":"Machine translation; Autoregressive model; Inference; Computer science; Transformer; Translation (biology); Artificial intelligence; BLEU; Machine learning; Artificial neural network; Econometrics; Mathematics; Engineering; Voltage","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00147905,0.001280548,0.000944799,0.0004692803,0.0003613285,0.001018981,0.001657462,0.0009317367,0.003702828],"category_scores_gemma":[0.004076821,0.0006318384,0.0008667991,0.0009319294,0.0005970473,0.002902902,0.0008473796,0.002449231,0.003095521],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000643138,"about_ca_system_score_gemma":0.001677444,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008760117,"about_ca_topic_score_gemma":0.01574124,"domain_scores_codex":[0.999355,0.0002082185,0.00004157683,0.0001984049,0.0001211288,0.00007557603],"domain_scores_gemma":[0.9987798,0.0005356051,0.0000812408,0.000332673,0.000230235,0.00004042121],"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":[0.0005713195,0.0002449333,0.002030323,0.000279758,0.000271238,0.0002367222,0.0001431045,0.4186108,0.02299865,0.01553807,0.01639308,0.522682],"study_design_scores_gemma":[0.00002122837,0.00003695814,0.0001462877,0.000008317203,0.00002997669,0.00004081513,0.000008987125,0.9868786,0.005770052,0.005819995,0.001230094,0.000008716263],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02884702,0.000791526,0.9558993,0.0006366577,0.0001672953,0.0000441655,0.0004154159,0.01002092,0.003177608],"genre_scores_gemma":[0.5960293,0.0006985641,0.3899154,0.0006215579,0.0001546311,0.0001268575,0.002225029,0.0008105575,0.009418105],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.008760117,"threshold_uncertainty_score":0.01741827,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0423277031369836,"score_gpt":0.2771226150452021,"score_spread":0.2347949119082186,"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."}}