{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,24]],"date-time":"2025-06-24T06:40:03Z","timestamp":1750747203301,"version":"3.41.0"},"reference-count":55,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/access.2025.3580635","type":"journal-article","created":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T17:41:34Z","timestamp":1750182094000},"page":"105101-105112","source":"Crossref","is-referenced-by-count":0,"title":["RMixDA: A Random Compound Data Augmentation Operation Framework for Neural Machine Translation"],"prefix":"10.1109","volume":"13","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-8423-4013","authenticated-orcid":false,"given":"Huijun","family":"Wang","sequence":"first","affiliation":[{"name":"School of Computer, Electronics Information, Guangxi University, Nanning, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5199-7192","authenticated-orcid":false,"given":"Xiaojing","family":"Du","sequence":"additional","affiliation":[{"name":"STEM, University of South Australia, Adelaide, SA, Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-4235-1014","authenticated-orcid":false,"given":"Xinkun","family":"Hao","sequence":"additional","affiliation":[{"name":"School of Computer, Electronics Information, Guangxi University, Nanning, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/E17-2101"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-97-1488-9_9"},{"key":"ref3","first-page":"1","article-title":"A comparison between NMT and PBSMT performance for translating noisy user-generated content","volume-title":"Proc. 22nd Nordic Conf. Comput. Linguistics","author":"N\u00fa\u00f1ez"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-45751-8_2"},{"key":"ref5","first-page":"186","article-title":"Rule-based machine translation","volume-title":"Routledge Encyclopedia of Translation Technology","author":"Shiwen","year":"2014"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref7","article-title":"Google\u2019s neural machine translation system: Bridging the gap between human and machine translation","author":"Wu","year":"2016","journal-title":"arXiv:1609.08144"},{"key":"ref8","article-title":"A simple but tough-to-beat data augmentation approach for natural language understanding and generation","author":"Shen","year":"2020","journal-title":"arXiv:2009.13818"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.array.2022.100258"},{"key":"ref10","first-page":"1","article-title":"Synthetic and natural noise both break neural machine translation","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Belinkov"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.529"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1020"},{"key":"ref13","first-page":"10890","article-title":"R-drop: Regularized dropout for neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Liang"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-acl.84"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/p17-2090"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/d18-1100"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.447"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/579"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/E17-1083"},{"key":"ref20","first-page":"1","article-title":"Data noising as smoothing in neural network language models","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Xie"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1045"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6233"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.lifelongnlp-1.3"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.194"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1163"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-1314"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1425"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-5506"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.48550\/arxiv.1710.09412"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00612"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1016\/j.aiopen.2022.03.001"},{"key":"ref32","first-page":"1","article-title":"Co-mixup: Saliency guided joint mixup with supermodular diversity","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Kim"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevLett.86.2050"},{"key":"ref34","first-page":"125","article-title":"The syntax and the semantics of the proposed international algebraic language of the Zurich ACM-GAMM conference","volume-title":"Proc. ICIP","author":"Backus"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1670"},{"key":"ref36","first-page":"1","article-title":"Unsupervised machine translation using monolingual corpora only","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Lample"},{"key":"ref37","first-page":"1","article-title":"Unsupervised neural machine translation","volume-title":"Proc. 6th Int. Conf. Learn. Represent.","author":"Artetxe"},{"key":"ref38","article-title":"Improving neural networks by preventing co-adaptation of feature detectors","author":"Hinton","year":"2012","journal-title":"arXiv:1207.0580"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.3115\/1708124.1708131"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.3150\/12-bejsp10"},{"article-title":"Dictionary of algorithms and data structures","year":"8318","author":"Black","key":"ref41"},{"issue":"1","key":"ref42","first-page":"39","article-title":"A maximum entropy approach to natural language processing","volume":"22","author":"Berger","year":"1996","journal-title":"Comput. Linguistics"},{"key":"ref43","first-page":"1","article-title":"An actor-critic algorithm for sequence prediction","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Bahdanau"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.534"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-99-4752-2_54"},{"key":"ref47","first-page":"1047","article-title":"SimCLNMT: A simple contrastive learning method for enhancing neural machine translation quality","volume-title":"Proc. 23rd Chin. Nat. Conf. Comput. Linguistics","author":"Menglong"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.3390\/electronics12102320"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.109"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1214\/21-BA1259"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01168"},{"issue":"120","key":"ref52","first-page":"1","article-title":"Switch transformers: Scaling to trillion parameter models with simple and efficient sparsity","volume":"23","author":"Fedus","year":"2022","journal-title":"J. Mach. Learn. Res."},{"key":"ref53","article-title":"Non-autoregressive neural machine translation","author":"Gu","year":"2017","journal-title":"arXiv:1711.02281"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1145\/3676536.3676778"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.3390\/app15084494"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/10820123\/11037679.pdf?arnumber=11037679","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,24]],"date-time":"2025-06-24T06:01:29Z","timestamp":1750744889000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11037679\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":55,"URL":"https:\/\/doi.org\/10.1109\/access.2025.3580635","relation":{},"ISSN":["2169-3536"],"issn-type":[{"type":"electronic","value":"2169-3536"}],"subject":[],"published":{"date-parts":[[2025]]}}}