{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,10]],"date-time":"2026-04-10T20:14:24Z","timestamp":1775852064545,"version":"3.50.1"},"reference-count":62,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"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":["U20A20229"],"award-info":[{"award-number":["U20A20229"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003995","name":"Natural Science Foundation of Anhui Province","doi-asserted-by":"publisher","award":["2008085J31"],"award-info":[{"award-number":["2008085J31"]}],"id":[{"id":"10.13039\/501100003995","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Alibaba Group through Alibaba Research Intern Program"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE\/ACM Trans. Audio Speech Lang. Process."],"published-print":{"date-parts":[[2021]]},"DOI":"10.1109\/taslp.2021.3076863","type":"journal-article","created":{"date-parts":[[2021,4,30]],"date-time":"2021-04-30T19:56:27Z","timestamp":1619812587000},"page":"1740-1751","source":"Crossref","is-referenced-by-count":28,"title":["Adaptive Adapters: An Efficient Way to Incorporate BERT Into Neural Machine Translation"],"prefix":"10.1109","volume":"29","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8360-5483","authenticated-orcid":false,"given":"Junliang","family":"Guo","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1385-3742","authenticated-orcid":false,"given":"Zhirui","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Linli","family":"Xu","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3170-4858","authenticated-orcid":false,"given":"Boxing","family":"Chen","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4835-4102","authenticated-orcid":false,"given":"Enhong","family":"Chen","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","first-page":"3011","article-title":"Fast structured decoding for sequence models","author":"sun","year":"0","journal-title":"Adv Neural Inf Process Syst"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33013723"},{"key":"ref33","first-page":"506","article-title":"Learning multiple visual domains with residual adapters","author":"rebuffi","year":"0","journal-title":"Adv Neural Inf Process Syst"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00313"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1139"},{"key":"ref30","article-title":"Distilling the knowledge in a neural network","author":"hinton","year":"2015"},{"key":"ref37","article-title":"Non-autoregressive neural machine translation","author":"gu","year":"2018","journal-title":"Int Conf on Learning Representations"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i01.5341"},{"key":"ref35","article-title":"K-adapter: Infusing knowledge into pre-trained models with adapters","author":"wang","year":"2020"},{"key":"ref34","first-page":"2790","article-title":"Parameter-efficient transfer learning for NLP","volume":"97","author":"houlsby","year":"0","journal-title":"Proc 36th Inter Conf Machine Learn"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref62","article-title":"Joint training for neural machine translation models with monolingual data","author":"zhang","year":"2018","journal-title":"Proc Thirty-Second AAAI Conf Arti Intel"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1045"},{"key":"ref28","first-page":"5926","article-title":"Mass: Masked sequence to sequence pre-training for language generation","volume":"97","author":"song","year":"0","journal-title":"Proc 36th Int Conf Machine Learn"},{"key":"ref27","first-page":"7057","article-title":"Cross-lingual language model pretraining","author":"lample","year":"2019","journal-title":"Adv Neural Info Proc Syst"},{"key":"ref29","first-page":"7871","article-title":"Bart: Denoising sequence-to-sequence pre-training for natural language generation, translation, and comprehension","author":"lewis","year":"0","journal-title":"Proc 58th Ann Meet Asso Comput Linguist"},{"key":"ref2","article-title":"Improving language understanding by generative pre-training","author":"radford","year":"2018"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-1202"},{"key":"ref20","article-title":"Reducing transformer depth on demand with structured dropout","author":"fan","year":"2020","journal-title":"Int Conf on Learning Representations"},{"key":"ref22","article-title":"Categorical reparameterization with gumbel-softmax","author":"jang","year":"2017","journal-title":"Int Conf Learn Represent"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.repl4nlp-1.18"},{"key":"ref24","first-page":"p. 9","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"radford","year":"2019","journal-title":"OpenAIRE blog"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1080\/01621459.2017.1285773"},{"key":"ref26","article-title":"Roberta: A. robustly optimized bert pretraining approach","author":"liu","year":"2019"},{"key":"ref25","first-page":"13042","article-title":"Unified language model pre-training for natural language understanding and generation","author":"dong","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1580"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2702"},{"key":"ref59","article-title":"Auto-encoding variational bayes","author":"kingma","year":"2014","journal-title":"Int Conf on Learning Representations"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref57","article-title":"Layer normalization","author":"ba","year":"2016"},{"key":"ref56","first-page":"9782","article-title":"Dynabert: Dynamic bert with adaptive width and depth","volume":"33","author":"hou","year":"2020","journal-title":"Adv Neural Inf Process Syst"},{"key":"ref55","article-title":"Distilbert, a distilled version of bert: Smaller, faster, cheaper and lighter","author":"sanh","year":"2019"},{"key":"ref54","first-page":"4163","article-title":"Tinybert: Distilling bert for natural language understanding","author":"jiao","year":"0","journal-title":"Proc Conf Empirical Methods Nat Lang Process Findings"},{"key":"ref53","article-title":"Distilling task-specific knowledge from bert into simple neural networks","author":"tang","year":"2019"},{"key":"ref52","first-page":"4163","article-title":"Deep transformers with latent depth","author":"li","year":"0","journal-title":"Proc Conf Empirical Methods Nat Lang Proc Findings"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/K16-1028"},{"key":"ref11","first-page":"9266","article-title":"Acquiring knowledge from pre-trained model to neural machine translation","author":"weng","year":"2020","journal-title":"Thirty-Fourth AAAI Conf Artif Intell"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6289"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6479"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.705"},{"key":"ref14","article-title":"Incorporating bert into neural machine translation","author":"zhu","year":"2020","journal-title":"Int Conf on Learning Representations"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/S0079-7421(08)60536-8"},{"key":"ref16","article-title":"Mixout: Effective regularization to finetune large-scale pretrained language models","author":"lee","year":"0","journal-title":"8th Inter Conf Learn Represent ICLR"},{"key":"ref17","first-page":"10843","article-title":"Incorporating bert into parallel sequence decoding with adapters","volume":"33","author":"guo","year":"2020","journal-title":"Adv Neural Inf Process Syst"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1165"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1633"},{"key":"ref4","first-page":"5754","article-title":"Generalized autoregressive pretraining for language understanding","author":"yang","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref3","first-page":"4171","article-title":"Bert:Pre-training of deep bidirectional transformers for language understanding","volume":"1","author":"devlin","year":"0","journal-title":"Proc Conf North Amer Ch Asso Comput Linguist Hum Langu Technol"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W18-5446"},{"key":"ref5","first-page":"1877","article-title":"Language models are few-shot learners","volume":"33","author":"brown","year":"2020","journal-title":"Adv in Neural Info Proc Syst"},{"key":"ref8","article-title":"Neural machine translation by jointly learning to align and translate","author":"bahdanau","year":"2015","journal-title":"Int Conf on Learning Representations"},{"key":"ref7","first-page":"2383","article-title":"Squad: 100000 questions for machine comprehension of text","author":"rajpurkar","year":"0","journal-title":"Proc Conf Empirical Methods Nat Lang Proc"},{"key":"ref49","article-title":"Rethinking the value of network pruning","author":"liu","year":"2019","journal-title":"Int Conf on Learning Representations"},{"key":"ref9","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref46","first-page":"2074","article-title":"Learning structured sparsity in deep neural networks","volume":"29","author":"wen","year":"2016","journal-title":"Adv Neural Inf Process Syst"},{"key":"ref45","article-title":"Pruning filters for efficient convnets","author":"li","year":"2017","journal-title":"Int Conf on Learning Representations"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00291"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.155"},{"key":"ref42","first-page":"11179","article-title":"Levenshtein transformer","author":"gu","year":"0","journal-title":"Adv Neural Inf Process Syst"},{"key":"ref41","first-page":"5976","article-title":"Insertion transformer: Flexible sequence generation via insertion operations","volume":"97","author":"stern","year":"0","journal-title":"Proc 36th Inter Conf Machine Learn"},{"key":"ref44","first-page":"598","article-title":"Optimal brain damage","volume":"2","author":"lecun","year":"1989","journal-title":"Adv Neural Inf Process Syst"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.36"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/9289074\/09420282.pdf?arnumber=9420282","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T14:53:55Z","timestamp":1652194435000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9420282\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"references-count":62,"URL":"https:\/\/doi.org\/10.1109\/taslp.2021.3076863","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021]]}}}