{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,4]],"date-time":"2026-03-04T17:18:07Z","timestamp":1772644687481,"version":"3.50.1"},"reference-count":57,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Key R&D Program of China","award":["2022ZD0162101"],"award-info":[{"award-number":["2022ZD0162101"]}]},{"DOI":"10.13039\/501100003399","name":"Science and Technology Commission of Shanghai Municipality","doi-asserted-by":"publisher","award":["21511101100"],"award-info":[{"award-number":["21511101100"]}],"id":[{"id":"10.13039\/501100003399","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003399","name":"Science and Technology Commission of Shanghai Municipality","doi-asserted-by":"publisher","award":["22DZ2229005"],"award-info":[{"award-number":["22DZ2229005"]}],"id":[{"id":"10.13039\/501100003399","id-type":"DOI","asserted-by":"publisher"}]},{"name":"111 plan","award":["BP0719010"],"award-info":[{"award-number":["BP0719010"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE\/ACM Trans. Audio Speech Lang. Process."],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/taslp.2024.3379884","type":"journal-article","created":{"date-parts":[[2024,3,20]],"date-time":"2024-03-20T18:30:46Z","timestamp":1710959446000},"page":"2100-2111","source":"Crossref","is-referenced-by-count":2,"title":["Leveraging Diverse Modeling Contexts With Collaborating Learning for Neural Machine Translation"],"prefix":"10.1109","volume":"32","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7549-3944","authenticated-orcid":false,"given":"Yusheng","family":"Liao","sequence":"first","affiliation":[{"name":"Cooperative Medianet Innovation Center, Shanghai Jiao Tong University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3196-2347","authenticated-orcid":false,"given":"Yanfeng","family":"Wang","sequence":"additional","affiliation":[{"name":"Cooperative Medianet Innovation Center, Shanghai Artificial Intelligence Laboratory, Shanghai Jiao Tong University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9500-081X","authenticated-orcid":false,"given":"Yu","family":"Wang","sequence":"additional","affiliation":[{"name":"Cooperative Medianet Innovation Center, Shanghai Artificial Intelligence Laboratory, Shanghai Jiao Tong University, Shanghai, China"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Non-autoregressive neural machine translation","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Gu","year":"2018"},{"key":"ref2","first-page":"5976","article-title":"Insertion transformer: Flexible sequence generation via insertion operations","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Stern","year":"2019"},{"key":"ref3","first-page":"11179","article-title":"Levenshtein transformer","volume-title":"Proc. 33rd Int. Conf. Neural Inf. Process. Syst.","author":"Gu","year":"2019"},{"key":"ref4","first-page":"5144","article-title":"Non-autoregressive machine translation with disentangled context transformer","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Kasai","year":"2020"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/d16-1139"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6465"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.615"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6479"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.705"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2946480"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.3301443"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00256"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.artint.2020.103234"},{"key":"ref14","first-page":"7528","article-title":"Knowledge distillation by on-the-fly native ensemble","volume-title":"Proc. 32nd Int. Conf. Neural Inf. Process. Syst.","author":"Lan","year":"2018"},{"key":"ref15","article-title":"Mutual mean-teaching: Pseudo label refinery for unsupervised domain adaptation on person re-identification","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Ge","year":"2020"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00454"},{"key":"ref17","article-title":"A generalized framework of sequence generation with application to undirected sequence models","author":"Mansimov","year":"2019"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.coling-main.25"},{"key":"ref19","first-page":"8630","article-title":"BANG: Bridging autoregressive and non-autoregressive generation with large scale pretraining","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Qi","year":"2021"},{"key":"ref20","first-page":"81","article-title":"Diformer: Directional transformer for neural machine translation","volume-title":"Proc. 23rd Annu. Conf. Eur. Assoc. Mach. Transl.","author":"Wang","year":"2022"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.findings-emnlp.155"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1633"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/taslp.2022.3221043"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00610"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58621-8_45"},{"key":"ref27","first-page":"4116","article-title":"Contrastive multi-view representation learning on graphs","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Hassani","year":"2020"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref29","article-title":"Representation learning with contrastive predictive coding","author":"Oord","year":"2018"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D15-1166"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P16-1008"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1164"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.552"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.393"},{"key":"ref35","article-title":"CLEAR: Contrastive learning for sentence representation","author":"Wu","year":"2020"},{"key":"ref36","article-title":"CERT: Contrastive self-supervised learning for language understanding","author":"Fang","year":"2020"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.3390\/app12105003"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.206"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.naacl-main.313"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-4009"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1149"},{"key":"ref42","first-page":"76","article-title":"Stanford neural machine translation systems for spoken language domains","volume-title":"Proc. 12th Int. Workshop Spoken Lang. Transl.: Eval. Campaign","author":"Luong","year":"2015"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P16-1162"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref45","article-title":"Adam: A method for stochastic optimization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kingma","year":"2015"},{"key":"ref46","article-title":"Semi-autoregressive training improves mask-predict decoding","author":"Ghazvininejad","year":"2020"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.265"},{"key":"ref48","article-title":"Improving non-autoregressive translation models without distillation","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Huang","year":"2022"},{"key":"ref49","first-page":"5513","article-title":"Helping the weak makes you strong: Simple multi-task learning improves non-autoregressive translators","volume-title":"Proc. Conf. Empirical Methods Natural Lang. Process.","author":"Wang","year":"2022"},{"key":"ref50","first-page":"2878","article-title":"Confidence based bidirectional global context aware training framework for neural machine translation","volume-title":"Proc. 60th Annu. Meeting Assoc. Computat. Linguistics","author":"Zhou","year":"2022"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.naacl-main.313"},{"key":"ref52","first-page":"8050","article-title":"JANUS: Joint autoregressive and non-autoregressive training with auxiliary loss for sequence generation","volume-title":"Proc. Conf. Empirical Methods Natural Lang. Process.","author":"Liang","year":"2022"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.213"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/w15-3049"},{"key":"ref55","first-page":"3515","article-title":"Aligned cross entropy for non-autoregressive machine translation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Ghazvininejad","year":"2020"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.83"},{"key":"ref57","first-page":"8630","article-title":"BANG: Bridging autoregressive and non-autoregressive generation with large scale pretraining","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Qi","year":"2021"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/10304349\/10476658.pdf?arnumber=10476658","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,4,9]],"date-time":"2024-04-09T19:45:55Z","timestamp":1712691955000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10476658\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":57,"URL":"https:\/\/doi.org\/10.1109\/taslp.2024.3379884","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}