{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,26]],"date-time":"2026-01-26T00:05:23Z","timestamp":1769385923933,"version":"3.49.0"},"reference-count":51,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"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":["62036004"],"award-info":[{"award-number":["62036004"]}],"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":[[2022]]},"DOI":"10.1109\/taslp.2022.3153264","type":"journal-article","created":{"date-parts":[[2022,2,28]],"date-time":"2022-02-28T21:46:56Z","timestamp":1646084816000},"page":"992-1002","source":"Crossref","is-referenced-by-count":16,"title":["Multi-Teacher Distillation With Single Model for Neural Machine Translation"],"prefix":"10.1109","volume":"30","author":[{"given":"Xiaobo","family":"Liang","sequence":"first","affiliation":[{"name":"Soochow University, Suzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3530-590X","authenticated-orcid":false,"given":"Lijun","family":"Wu","sequence":"additional","affiliation":[{"name":"Microsoft Research, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6286-7529","authenticated-orcid":false,"given":"Juntao","family":"Li","sequence":"additional","affiliation":[{"name":"Soochow University, Suzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9095-0776","authenticated-orcid":false,"given":"Tao","family":"Qin","sequence":"additional","affiliation":[{"name":"Microsoft Research, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Min","family":"Zhang","sequence":"additional","affiliation":[{"name":"Soochow University, Suzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tie-Yan","family":"Liu","sequence":"additional","affiliation":[{"name":"Microsoft Research, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","first-page":"3104","article-title":"Sequence to sequence learning with neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"27","author":"Sutskever","year":"2014"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1146\/annurev.neuro.26.041002.131047"},{"key":"ref3","article-title":"Attention is all you need","volume-title":"Adv. Neural Inf. Process. Syst.","volume":"30","author":"Vaswani","year":"2017"},{"key":"ref4","first-page":"1243","article-title":"Convolutional sequence to sequence learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Gehring","year":"2017"},{"key":"ref5","article-title":"Distilling the knowledge in a neural network","volume-title":"Stat","volume":"1050","author":"Hinton","year":"2015"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/d16-1139"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.324"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.coling-main.302"},{"key":"ref9","article-title":"Multilingual neural machine translation with knowledge distillation","volume-title":"Int. Conf. Learn. Representations","author":"Tan","year":"2019"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-1192"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.494"},{"key":"ref12","first-page":"10 018","article-title":"Data diversification: A simple strategy for neural machine translation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Nguyen","year":"2020"},{"key":"ref13","first-page":"1613","article-title":"Weight uncertainty in neural network","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Blundell","year":"2015"},{"key":"ref14","article-title":"IoT: Instance-wise layer reordering for transformer structures","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zhu","year":"2021"},{"key":"ref15","article-title":"Reducing transformer depth on demand with structured dropout","volume-title":"Int. Conf. Learn. Representations","author":"Fan","year":"2019"},{"issue":"1","key":"ref16","first-page":"1929","article-title":"Dropout: A simple way to prevent neural networks from overfitting","volume":"15","author":"Srivastava","year":"2014","journal-title":"J. Mach. Learn. Res."},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/1150402.1150464"},{"key":"ref18","first-page":"2654","article-title":"Do deep nets really need to be deep","volume-title":"Proc. 27th Int. Conf. Neural Inf. Process. Syst.","volume":"2","author":"Ba","year":"2014"},{"key":"ref19","article-title":"Policy distillation","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Rusu","year":"2016"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682450"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-1382"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/3336191.3371792"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.repl4nlp-1.10"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.304"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.26615\/978-954-452-056-4_050"},{"key":"ref26","article-title":"Understanding knowledge distillation in non-autoregressive machine translation","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zhou","year":"2019"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.74"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.ngt-1.12"},{"key":"ref29","article-title":"Ensemble distillation for neural machine translation","author":"Freitag","year":"2017"},{"key":"ref30","first-page":"3956","article-title":"Analyzing uncertainty in neural machine translation","volume-title":"Proc. Int. Conf. Mach. Learning","author":"Ott","year":"2018"},{"key":"ref31","article-title":"The lottery ticket hypothesis: Finding sparse, trainable neural networks","volume-title":"Int. Conf. Learn. Representations","author":"Frankle","year":"2018"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.270"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.naacl-main.302"},{"key":"ref34","article-title":"Report on the 11th IWSLT evaluation campaign, IWSLT 2014","volume-title":"Proc. Int. Workshop Spoken Lang. Transl., Eval. Campaign","volume":"57","author":"Cettolo","year":"2014"},{"key":"ref35","first-page":"2","article-title":"Overview of the IWSLT 2017 evaluation campaign","volume-title":"Proc. Int. Workshop Spoken Lang. Transl.","author":"Cettolo","year":"2017"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P16-1162"},{"key":"ref37","article-title":"Adam: A method for stochastic optimization","volume-title":"Int. Conf. Learn. Representations","author":"Kingma","year":"2015"},{"key":"ref38","article-title":"Pay less attention with lightweight and dynamic convolutions","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Wu","year":"2019"},{"key":"ref39","article-title":"Understanding and improving transformer from a multi-particle dynamic system point of view","volume-title":"ICLR 2020 Workshop Integration Deep Neural Models Differential Equations","author":"Lu","year":"2020"},{"key":"ref40","article-title":"Multi-agent dual learning","volume-title":"Proc. 7th Int. Conf. Learn. Representations","author":"Wang","year":"2019"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i11.17127"},{"key":"ref42","article-title":"Multi-branch attentive transformer","author":"Fan","year":"2020"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-2074"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W18-6301"},{"key":"ref45","first-page":"5877","article-title":"The evolved transformer","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"So","year":"2019"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1045"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N16-1014"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W19-2311"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1633"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.eacl-main.25"},{"key":"ref51","article-title":"Bertscore: Evaluating text generation with bert","volume-title":"Int. Conf. Learn. Representations","author":"Zhang","year":"2019"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/9657755\/09722996.pdf?arnumber=9722996","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,17]],"date-time":"2024-01-17T23:50:58Z","timestamp":1705535458000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9722996\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"references-count":51,"URL":"https:\/\/doi.org\/10.1109\/taslp.2022.3153264","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022]]}}}