{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T12:39:18Z","timestamp":1761395958259,"version":"3.37.3"},"reference-count":57,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"8","license":[{"start":{"date-parts":[[2022,8,1]],"date-time":"2022-08-01T00:00:00Z","timestamp":1659312000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,8,1]],"date-time":"2022-08-01T00:00:00Z","timestamp":1659312000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,8,1]],"date-time":"2022-08-01T00:00:00Z","timestamp":1659312000000},"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":["61702121","61772378"],"award-info":[{"award-number":["61702121","61772378"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"National Philosophy Social Science Major Bidding Project","award":["11&zd189"],"award-info":[{"award-number":["11&zd189"]}]},{"DOI":"10.13039\/501100019048","name":"Research Foundation of Ministry of Education of China","doi-asserted-by":"publisher","award":["18JZD015"],"award-info":[{"award-number":["18JZD015"]}],"id":[{"id":"10.13039\/501100019048","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Key Project of State Language Commission of China","award":["ZDI135-112"],"award-info":[{"award-number":["ZDI135-112"]}]},{"name":"Guangdong Basic and Applied Basic Research Foundation of China","award":["2020A151501705"],"award-info":[{"award-number":["2020A151501705"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Neural Netw. Learning Syst."],"published-print":{"date-parts":[[2022,8]]},"DOI":"10.1109\/tnnls.2021.3053633","type":"journal-article","created":{"date-parts":[[2021,2,12]],"date-time":"2021-02-12T17:42:35Z","timestamp":1613151755000},"page":"3612-3621","source":"Crossref","is-referenced-by-count":20,"title":["Optimizing Attention for Sequence Modeling via Reinforcement Learning"],"prefix":"10.1109","volume":"33","author":[{"given":"Hao","family":"Fei","sequence":"first","affiliation":[{"name":"School of Cyber Science and Engineering, Wuhan University, Wuhan, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5214-2268","authenticated-orcid":false,"given":"Yue","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Engineering, Westlake University, Hangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0291-4733","authenticated-orcid":false,"given":"Yafeng","family":"Ren","sequence":"additional","affiliation":[{"name":"School of Interpreting and Translation, Guangdong University of Foreign Studies, Guangzhou, China"}]},{"given":"Donghong","family":"Ji","sequence":"additional","affiliation":[{"name":"School of Cyber Science and Engineering, Wuhan University, Wuhan, China"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Neural machine translation by jointly learning to align and translate","author":"Bahdanau","year":"2014","journal-title":"arXiv:1409.0473"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D15-1166"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/P15-1152"},{"key":"ref4","article-title":"Bidirectional attention flow for machine comprehension","author":"Seo","year":"2016","journal-title":"arXiv:1611.01603"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12142"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.10974"},{"key":"ref7","article-title":"Show, attend and tell: Neural image caption generation with visual attention","author":"Xu","year":"2015","journal-title":"arXiv:1502.03044"},{"key":"ref8","article-title":"Morphological inflection generation with hard monotonic attention","author":"Aharoni","year":"2016","journal-title":"arXiv:1611.01487"},{"key":"ref9","article-title":"Overcoming catastrophic forgetting with hard attention to the task","author":"Serr\u00e0","year":"2018","journal-title":"arXiv:1801.01423"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11941"},{"key":"ref11","first-page":"5998","article-title":"Attention is all you need","volume-title":"Proc. Conf. Workshop Neural Inf. Process. Syst.","author":"Vaswani"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.18653\/vl\/N19-142"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12054"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W18-6318"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W17-4711"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.419"},{"key":"ref17","first-page":"3338","article-title":"A regularized framework for sparse and structured neural attention","volume-title":"Proc. Conf. Workshop Neural Inf. Process. Syst.","author":"Niculae"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/644"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1053"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12047"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2017\/568"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2019.2957276"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-32233-5_50"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6271"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2019.10.065"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/617"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/604"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1030"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1098"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.168"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1218"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1445"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1286"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1002"},{"key":"ref35","first-page":"3543","article-title":"Attention is not explanation","volume-title":"Proc. Conf. North Amer. Chapter Assoc.","author":"Jain"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1282"},{"key":"ref37","first-page":"820","article-title":"Dual learning for machine translation","volume-title":"Proc. 13th Annu. Conf. Neural Inf. Process. Syst.","author":"He"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.10804"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D17-1063"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-1113"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/IALP.2018.8629107"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1290"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ACC.2012.6315022"},{"volume-title":"Reinforcement Learning: An Introduction","year":"2018","author":"Sutton","key":"ref44"},{"key":"ref45","first-page":"1","article-title":"Continuous control with deep reinforcement learning","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Lillicrap"},{"key":"ref46","first-page":"387","article-title":"Deterministic policy gradient algorithms","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Silver"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/bf00992696"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/d16-1171"},{"key":"ref49","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014","journal-title":"arXiv:1412.6980"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1181"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-02922-7_31"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.3115\/1219840.1219855"},{"key":"ref54","first-page":"1631","article-title":"Recursive deep models for semantic compositionality over a sentiment treebank","volume-title":"Proc. Conf. Empirical Methods Natural Lang. Process.","author":"Socher"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.3115\/1218955.1218990"},{"key":"ref56","first-page":"649","article-title":"Character-level convolutional networks for text classification","volume-title":"Proc. Conf. Workshop Neural Inf. Process. Syst.","author":"Zhang"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/d16-1058"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/5962385\/9849214\/09352534.pdf?arnumber=9352534","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,10]],"date-time":"2024-01-10T00:19:05Z","timestamp":1704845945000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9352534\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,8]]},"references-count":57,"journal-issue":{"issue":"8"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2021.3053633","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"type":"print","value":"2162-237X"},{"type":"electronic","value":"2162-2388"}],"subject":[],"published":{"date-parts":[[2022,8]]}}}