{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,8]],"date-time":"2026-01-08T08:10:23Z","timestamp":1767859823187,"version":"3.49.0"},"reference-count":60,"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":["U1636211"],"award-info":[{"award-number":["U1636211"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61672081"],"award-info":[{"award-number":["61672081"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61370126"],"award-info":[{"award-number":["61370126"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"2022 Tencent Wechat Rhino-Bird Focused Research Program"},{"name":"Fund of the State Key Laboratory of Software Development Environment","award":["SKLSDE-2021ZX-18"],"award-info":[{"award-number":["SKLSDE-2021ZX-18"]}]}],"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.2022.3221040","type":"journal-article","created":{"date-parts":[[2022,11,10]],"date-time":"2022-11-10T20:37:31Z","timestamp":1668112651000},"page":"1489-1498","source":"Crossref","is-referenced-by-count":21,"title":["GTrans: Grouping and Fusing Transformer Layers for Neural Machine Translation"],"prefix":"10.1109","volume":"31","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1983-012X","authenticated-orcid":false,"given":"Jian","family":"Yang","sequence":"first","affiliation":[{"name":"State Key Lab of Software Development Environment, Beihang University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5022-6468","authenticated-orcid":false,"given":"Yuwei","family":"Yin","sequence":"additional","affiliation":[{"name":"NLC Team, Microsoft Research Asia, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3391-4787","authenticated-orcid":false,"given":"Liqun","family":"Yang","sequence":"additional","affiliation":[{"name":"School of Cyber Science and Technology, Beihang University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shuming","family":"Ma","sequence":"additional","affiliation":[{"name":"NLC Team, Microsoft Research Asia, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haoyang","family":"Huang","sequence":"additional","affiliation":[{"name":"NLC Team, Microsoft Research Asia, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0833-7903","authenticated-orcid":false,"given":"Dongdong","family":"Zhang","sequence":"additional","affiliation":[{"name":"NLC Team, Microsoft Research Asia, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Furu","family":"Wei","sequence":"additional","affiliation":[{"name":"NLC Team, Microsoft Research Asia, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9603-9713","authenticated-orcid":false,"given":"Zhoujun","family":"Li","sequence":"additional","affiliation":[{"name":"State Key Lab of Software Development Environment, Beihang University, 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. 27th Int. Conf. Neural Inf. Process. Syst.","author":"Sutskever","year":"2014"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CLUSTER.2019.8891019"},{"key":"ref3","first-page":"1243","article-title":"Convolutional sequence to sequence learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Gehring","year":"2017"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1008"},{"key":"ref5","first-page":"5998","article-title":"Attention is all you need","volume-title":"Proc. Neural Inf. Process. Syst.","author":"Vaswani"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W18-6422"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.463"},{"key":"ref8","first-page":"7955","article-title":"Layer-wise coordination between encoder and decoder for neural machine translation","volume-title":"Proc. Neural Inf. Process. Syst.","author":"He","year":"2018"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/p19-1176"},{"key":"ref10","first-page":"1352","article-title":"Rezero is all you need: Fast convergence at large depth","volume-title":"Proc. 37th Conf. Uncertainty Artif. Intell.","author":"Bachlechner","year":"2021"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.38"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.72"},{"key":"ref13","first-page":"1736","article-title":"Deep transformers with latent depth","volume-title":"Proc. 34th Int. Conf. Neural Inf. Process. Syst.","author":"Li","year":"2020"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.463"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1338"},{"key":"ref16","first-page":"10524","article-title":"On layer normalization in the transformer architecture","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Xiong","year":"2020"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.40"},{"key":"ref18","first-page":"3015","article-title":"Multi-layer representation fusion for neural machine translation","volume-title":"Proc. 27th Int. Conf. Comput. Linguistics","author":"Wang","year":"2018"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.148"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00065"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.747"},{"key":"ref22","first-page":"1","article-title":"Beyond english-centric multilingual machine translation","volume":"22","author":"Fan","year":"2021","journal-title":"J. Mach. Learn. Res."},{"key":"ref23","first-page":"446","article-title":"Multilingual machine translation systems from microsoft for WMT21 shared task","volume-title":"Proc. 6th Conf. Mach. Transl.","author":"Yang","year":"2021"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.3115\/1557769.1557821"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P16-1162"},{"key":"ref26","article-title":"XLM-T: Scaling up multilingual machine translation with pretrained cross-lingual transformer encoders","author":"Ma","year":"2020"},{"key":"ref27","first-page":"1","article-title":"Pay less attention with lightweight and dynamic convolutions","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Wu","year":"2019"},{"key":"ref28","article-title":"DeltaLM: Encoder-decoder pre-training for language generation and translation by augmenting pretrained multilingual encoders","author":"Ma","year":"2021"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1558"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2018.2864648"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3057831"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3042006"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3076863"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3097939"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1146\/annurev.neuro.26.041002.131047"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-1012"},{"key":"ref38","article-title":"Longformer: The long-document transformer","author":"Beltagy","year":"2020"},{"key":"ref39","first-page":"1","article-title":"Reformer: The efficient transformer","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kitaev","year":"2020"},{"key":"ref40","first-page":"1","article-title":"Rethinking attention with performers","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Choromanski","year":"2021"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i12.17325"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.7"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.330186"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1083"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2876404"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1457"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-1388"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.eacl-main.138"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-acl.304"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1326"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1089"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.21"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.106"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-39431-8_43"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.coling-main.377"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.243"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1064"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11929"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.165"},{"key":"ref60","first-page":"1","article-title":"Understanding and improving encoder layer fusion in sequence-to-sequence learning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Liu","year":"2021"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/9970249\/09944969.pdf?arnumber=9944969","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,1]],"date-time":"2024-02-01T03:28:20Z","timestamp":1706758100000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9944969\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":60,"URL":"https:\/\/doi.org\/10.1109\/taslp.2022.3221040","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]}}}