{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,8]],"date-time":"2026-01-08T06:34:50Z","timestamp":1767854090392,"version":"3.49.0"},"reference-count":44,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"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":["U1836221"],"award-info":[{"award-number":["U1836221"]}],"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":["61772261"],"award-info":[{"award-number":["61772261"]}],"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":["61672277"],"award-info":[{"award-number":["61672277"]}],"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":[[2020]]},"DOI":"10.1109\/taslp.2020.2996807","type":"journal-article","created":{"date-parts":[[2020,5,22]],"date-time":"2020-05-22T20:50:40Z","timestamp":1590180640000},"page":"1707-1716","source":"Crossref","is-referenced-by-count":16,"title":["Improving Self-Attention Networks With Sequential Relations"],"prefix":"10.1109","volume":"28","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0717-505X","authenticated-orcid":false,"given":"Zaixiang","family":"Zheng","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shujian","family":"Huang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rongxiang","family":"Weng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xin-Yu","family":"Dai","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiajun","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1008"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1354"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1198"},{"key":"ref32","first-page":"1631","article-title":"Recursive deep models for semantic compositionality over a sentiment treebank","author":"socher","year":"0","journal-title":"Proc Empirical Methods Natural Lang Process"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.308"},{"key":"ref37","first-page":"2440","article-title":"End-to-end memory networks","author":"sukhbaatar","year":"0","journal-title":"Proc Neural Inf Process Syst"},{"key":"ref36","first-page":"3104","article-title":"Sequence to sequence learning with neural networks","author":"sutskever","year":"0","journal-title":"Proc Neural Inf Process Syst"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/78.650093"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D17-1013"},{"key":"ref10","first-page":"5070","article-title":"Meta multi-task learning for sequence modeling","author":"chen","year":"0","journal-title":"Proc Assoc Advance Artif Intell"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-1122"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1039"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1166"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P16-1139"},{"key":"ref14","article-title":"Learning natural language inference using bidirectional lstm model and inner-attention","author":"liu","year":"2016","journal-title":"arXiv 1605 09090 [cs]"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/604"},{"key":"ref16","first-page":"1815","article-title":"Enhancing sentence embedding with generalized pooling","author":"chen","year":"0","journal-title":"Proc Int Conf Comput Linguistics"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1176"},{"key":"ref18","article-title":"Dynamic self-attention: Computing attention over words dynamically for sentence embedding","author":"yoon","year":"0","journal-title":"arXiv 1808 07383"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D15-1075"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1174"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-2074"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1139"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1285"},{"key":"ref6","first-page":"5446","article-title":"DiSAN: Directional self-attention network for RNN\/CNN-free language understanding","author":"shen","year":"0","journal-title":"Proc Assoc Advance Artif Intell"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P16-1162"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1249"},{"key":"ref8","article-title":"Distance-based self-attention network for natural language inference","author":"im","year":"2017","journal-title":"arXiv 1712 02047"},{"key":"ref7","article-title":"Bi-directional block self-attention for fast and memory-efficient sequence modeling","author":"shen","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref2","first-page":"4171","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"devlin","year":"0","journal-title":"Proc Annu Conf North Amer Chapter Assoc Comput Linguistics Human Lang Technol"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D15-1166"},{"key":"ref1","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"0","journal-title":"Proc Neural Inf Process Syst"},{"key":"ref20","first-page":"2518","article-title":"Coupling distributed and symbolic execution for natural language queries","author":"mou","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"},{"key":"ref21","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2946480"},{"key":"ref24","article-title":"Google's neural machine translation system: Bridging the gap between human and machine translation","author":"wu","year":"2016","journal-title":"arXiv 1609 08144"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2017.2751420"},{"key":"ref23","first-page":"176","article-title":"Better hypothesis testing for statistical machine translation: Controlling for optimizer instability","author":"clark","year":"0","journal-title":"Proc Assoc Comput Linguistics"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-1202"},{"key":"ref26","article-title":"Non-Autoregressive Neural Machine Translation","author":"gu","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33016367"},{"key":"ref25","first-page":"1243","article-title":"Convolutional sequence to sequence learning","author":"gehring","year":"0","journal-title":"Proc Int Conf Mach Learn"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/8938144\/09099090.pdf?arnumber=9099090","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T17:31:43Z","timestamp":1651080703000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9099090\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"references-count":44,"URL":"https:\/\/doi.org\/10.1109\/taslp.2020.2996807","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020]]}}}