{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,28]],"date-time":"2026-01-28T21:25:13Z","timestamp":1769635513139,"version":"3.49.0"},"reference-count":45,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61876120"],"award-info":[{"award-number":["61876120"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE\/ACM Trans. Audio Speech Lang. Process."],"published-print":{"date-parts":[[2023]]},"DOI":"10.1109\/taslp.2023.3277245","type":"journal-article","created":{"date-parts":[[2023,5,17]],"date-time":"2023-05-17T17:33:40Z","timestamp":1684344820000},"page":"2079-2089","source":"Crossref","is-referenced-by-count":5,"title":["Alleviating Exposure Bias for Neural Machine Translation via Contextual Augmentation and Self Distillation"],"prefix":"10.1109","volume":"31","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6553-4236","authenticated-orcid":false,"given":"Zhidong","family":"Liu","sequence":"first","affiliation":[{"name":"School of Computer Science and Technology, Soochow University, Suzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7829-6348","authenticated-orcid":false,"given":"Junhui","family":"Li","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Soochow University, Suzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6519-2379","authenticated-orcid":false,"given":"Muhua","family":"Zhu","sequence":"additional","affiliation":[{"name":"Meituan Inc., Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.528"},{"key":"ref35","first-page":"4171","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"devlin","year":"0","journal-title":"Proc North Amer Chapter Assoc Comput Linguistics Hum Lang Technol"},{"key":"ref12","article-title":"Contrastive learning with adversarial perturbations for conditional text generation","author":"lee","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P16-1162"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1555"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-4012"},{"key":"ref14","article-title":"Data noising as smoothing in neural network language models","author":"xie","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-demos.6"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00381"},{"key":"ref30","article-title":"Improving BERT fine-tuning via self-ensemble and self-distillation","author":"xu","year":"2020"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-2072"},{"key":"ref33","first-page":"6256","article-title":"Unsupervised data augmentation for consistency training","author":"xie","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1510"},{"key":"ref32","first-page":"1218","article-title":"RoBERTa: A robustly optimized BERT pretraining approach","author":"liu","year":"0","journal-title":"Proc 20th Chin Nat Conf Comput Linguistics"},{"key":"ref2","article-title":"Neural machine translation by jointly learning to align and translate","author":"bahdanau","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref1","first-page":"3104","article-title":"Sequence to sequence learning with neural networks","author":"sutskever","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref17","first-page":"649","article-title":"Character-level convolutional networks for text classification","author":"zhang","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref39","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P16-1009"},{"key":"ref38","first-page":"8024","article-title":"PyTorch: An imperative style, high-performance deep learning library","author":"paszke","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/219717.219748"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3366423.3380144"},{"key":"ref24","first-page":"18","article-title":"Data augmentation using pre-trained transformer models","author":"kumar","year":"0","journal-title":"Proc 2nd Workshop Life-Long Learn Spoken Lang Syst"},{"key":"ref23","article-title":"A simple but tough-to-beat data augmentation approach for natural language understanding and generation","author":"shen","year":"2020"},{"key":"ref45","article-title":"Unsupervised machine translation using monolingual corpora only","author":"lample","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref26","first-page":"1607","article-title":"Born again neural networks","author":"furlanello","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref25","article-title":"Distilling the knowledge in a neural network","author":"hinton","year":"2015"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D15-1306"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2021\/534"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2020\/538"},{"key":"ref22","article-title":"Unsupervised neural machine translation","author":"artetxe","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1670"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/P15-1162"},{"key":"ref43","first-page":"388","article-title":"Statistical significance tests for machine translation evaluation","author":"koehn","year":"0","journal-title":"Proc Conf Empirical Methods Natural Lang Process"},{"key":"ref28","article-title":"FitNets: Hints for thin deep nets","author":"romero","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref27","article-title":"DistilBERT, A distilled version of BERT: Smaller, faster, cheaper and lighter","author":"sanh","year":"2019"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-1192"},{"key":"ref8","article-title":"Sequence level training with recurrent neural networks","author":"ranzato","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.artint.2020.103234"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P16-1159"},{"key":"ref4","first-page":"1171","article-title":"Scheduled sampling for sequence prediction with recurrent neural networks","author":"bengio","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref3","first-page":"6000","article-title":"Attention is all you need","author":"vaswani","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00256"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1426"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/9970249\/10128685.pdf?arnumber=10128685","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,6,19]],"date-time":"2023-06-19T18:18:47Z","timestamp":1687198727000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10128685\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":45,"URL":"https:\/\/doi.org\/10.1109\/taslp.2023.3277245","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]}}}