{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,13]],"date-time":"2026-03-13T06:18:09Z","timestamp":1773382689713,"version":"3.50.1"},"reference-count":45,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2019,3,1]],"date-time":"2019-03-01T00:00:00Z","timestamp":1551398400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,3,1]],"date-time":"2019-03-01T00:00:00Z","timestamp":1551398400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,3,1]],"date-time":"2019-03-01T00:00:00Z","timestamp":1551398400000},"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":["61673380"],"award-info":[{"award-number":["61673380"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Beijing Advanced Innovation for Language Resources of Beijing Language and Culture University"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE\/ACM Trans. Audio Speech Lang. Process."],"published-print":{"date-parts":[[2019,3]]},"DOI":"10.1109\/taslp.2018.2883740","type":"journal-article","created":{"date-parts":[[2018,11,28]],"date-time":"2018-11-28T20:19:27Z","timestamp":1543436367000},"page":"507-518","source":"Crossref","is-referenced-by-count":23,"title":["Attention With Sparsity Regularization for Neural Machine Translation and Summarization"],"prefix":"10.1109","volume":"27","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5293-7434","authenticated-orcid":false,"given":"Jiajun","family":"Zhang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yang","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2368-7541","authenticated-orcid":false,"given":"Haoran","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chengqing","family":"Zong","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","first-page":"2121","article-title":"Adaptive subgradient methods for online learning and stochastic optimization","volume":"12","author":"duchi","year":"2011","journal-title":"J Mach Learn Res"},{"key":"ref38","first-page":"3075","article-title":"SummaRuNNer: A recurrent neural network based sequence model for extractive summarization of documents","author":"nallapati","year":"0","journal-title":"Proc Assoc Adv Artif Intell"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P16-1162"},{"key":"ref32","doi-asserted-by":"crossref","first-page":"371","DOI":"10.1162\/tacl_a_00105","article-title":"Deep recurrent models with fast-forward connections for neural machine translation","volume":"4","author":"zhou","year":"2016","journal-title":"Transactions of the Association for Computational Linguistics"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P16-1159"},{"key":"ref30","article-title":"Subgradient methods","author":"vandenberghe","year":"2013"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/K16-1028"},{"key":"ref36","first-page":"1693","article-title":"Teaching machines to read and comprehend","author":"hermann","year":"0","journal-title":"Proc Neural Inf Process Syst"},{"key":"ref35","first-page":"388","article-title":"Statistical significance tests for machine translation evaluation","author":"koehn","year":"0","journal-title":"Proc Conf Empirical Methods Natural Lang Process"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref10","first-page":"5998","article-title":"Attention is all you need","author":"vawani","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref40","first-page":"74","article-title":"ROUGE: A package for automatic evaluation of summaries","author":"lin","year":"0","journal-title":"Proc Workshop Text Summarization Branches Out"},{"key":"ref11","first-page":"1","article-title":"An empirical study of adequate vision span for attention-based neural machine translation","author":"shu","year":"0","journal-title":"Proc 1st Workshop Neural Mach Transl"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.3115\/1557769.1557821"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P16-1008"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1096"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N16-1102"},{"key":"ref16","first-page":"3082","article-title":"Improving attention modeling with implicit distortion and fertility for machine translation","author":"feng","year":"0","journal-title":"Proc 26th Int Conf Comput Linguistics"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1249"},{"key":"ref18","first-page":"3093","article-title":"Neural machine translation with supervised attention","author":"liu","year":"0","journal-title":"Proc 26th Int Conf Comput Linguistics"},{"key":"ref19","first-page":"1614","article-title":"From Softmax to Sparsemax: A sparse model of attention and multi-label classification","author":"martins","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1162\/089976699300016395"},{"key":"ref4","article-title":"Google's neural machine translation system: Bridging the gap between human and machine translation","author":"wu","year":"2016"},{"key":"ref27","first-page":"39","article-title":"A maximum entropy approach to natural language processing","volume":"22","author":"berger","year":"1996","journal-title":"Comput Linguistics"},{"key":"ref3","article-title":"Is neural machine translation ready for deployment? A case study on 30 translation directions","author":"junczys-dowmunt","year":"2016","journal-title":"Proc 13th Int Workshop Spoken Lang Process"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N16-1012"},{"key":"ref29","first-page":"529","article-title":"Semi-supervised learning by entropy minimization","author":"grandvalet","year":"0","journal-title":"Proc Neural Inf Process Syst"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D15-1044"},{"key":"ref8","first-page":"2048","article-title":"Show, attend and tell: Neural image caption generation with visual attention","author":"xu","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-1099"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D15-1166"},{"key":"ref9","first-page":"1243","article-title":"Convolutional sequence to sequence learning","author":"gehring","year":"0","journal-title":"Proc Int Conf Mach Learning"},{"key":"ref1","article-title":"Neural machine translation by jointly learning to align and translate","author":"bahdanau","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref20","first-page":"3340","article-title":"A regularized framework for sparse and structured neural attention","author":"niculae","year":"0","journal-title":"Proc Neural Inf Process Syst"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-1101"},{"key":"ref22","article-title":"Distilling the knowledge in a neural network","author":"hinton","year":"0","journal-title":"NIPS 2014 Deep Learning Workshop"},{"key":"ref21","first-page":"370","article-title":"Sparse and constrained attention for neural machine translation","author":"malaviya","year":"0","journal-title":"Proc Annual Meeting of the Assoc Computational Linguistics"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1162\/089120103321337421"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref41","first-page":"2295","article-title":"Contrastive unsupervised word alignment with non-local features","author":"liu","year":"0","journal-title":"Proc 29th AAAI Conf Artif Intell"},{"key":"ref23","article-title":"Categorical reparameterization with Gumbel-Softmax","author":"jang","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-1098"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2007.70824"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P16-1154"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2006.253"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/8579631\/08550728.pdf?arnumber=8550728","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,13]],"date-time":"2022-07-13T20:43:51Z","timestamp":1657745031000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8550728\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,3]]},"references-count":45,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/taslp.2018.2883740","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019,3]]}}}