{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,6]],"date-time":"2025-12-06T17:10:08Z","timestamp":1765041008924,"version":"3.37.3"},"reference-count":54,"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":["61525205","61673289"],"award-info":[{"award-number":["61525205","61673289"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Alibaba Group through Alibaba Innovative Research Program"}],"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.2020.2998278","type":"journal-article","created":{"date-parts":[[2020,5,28]],"date-time":"2020-05-28T20:45:32Z","timestamp":1590698732000},"page":"1801-1812","source":"Crossref","is-referenced-by-count":7,"title":["Towards Better Word Alignment in Transformer"],"prefix":"10.1109","volume":"28","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1851-3264","authenticated-orcid":false,"given":"Kai","family":"Song","sequence":"first","affiliation":[]},{"given":"Xiaoqing","family":"Zhou","sequence":"additional","affiliation":[]},{"given":"Heng","family":"Yu","sequence":"additional","affiliation":[]},{"given":"Zhongqiang","family":"Huang","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5214-2268","authenticated-orcid":false,"given":"Yue","family":"Zhang","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5002-6933","authenticated-orcid":false,"given":"Weihua","family":"Luo","sequence":"additional","affiliation":[]},{"given":"Xiangyu","family":"Duan","sequence":"additional","affiliation":[]},{"given":"Min","family":"Zhang","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P16-1162"},{"key":"ref38","article-title":"Dynamic evaluation of transformer language models","volume":"abs 1904 8378","author":"krause","year":"2019"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/E17-2025"},{"key":"ref32","article-title":"Layer normalization","volume":"abs 1607 6450","author":"ba","year":"2016","journal-title":"CoRR"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1162\/089120103321337421"},{"key":"ref30","article-title":"Unsupervised machine translation using monolingual corpora only","author":"lample","year":"2018","journal-title":"Proc Intl Conf on Learning Representations"},{"key":"ref37","first-page":"2771","article-title":"Dynamic evaluation of neural sequence models","author":"krause","year":"0","journal-title":"Proc 35th Int Conf Mach Learn"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W17-3204"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-2081"},{"article-title":"Systran's pure neural machine translation systems","year":"2016","author":"crego","key":"ref34"},{"article-title":"Improving language understanding by generative pre-training","year":"2018","author":"radford","key":"ref28"},{"key":"ref27","first-page":"4171","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","volume":"1","author":"devlin","year":"2019","journal-title":"Proc Conf North American Chapter Assoc Comput Linguistics Human Lang Technologies"},{"key":"ref29","first-page":"70577067","article-title":"Cross-lingual language model pretraining","author":"lample","year":"0","journal-title":"Proc Adv Neural Inf Process Syst Annu Conf Neural Inf Process Syst"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.21236\/ADA461156"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-45751-8_2"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-1099"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W19-5201"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/730"},{"key":"ref24","article-title":"Adding interpretable attention to neural translation models improves word alignment","volume":"abs 1901 11359","author":"zenkel","year":"2019","journal-title":"CoRR"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1453"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1162\/089120103321337421"},{"key":"ref25","first-page":"263","article-title":"The mathematics of statistical machine translation: Parameter estimation","volume":"19","author":"brown","year":"1993","journal-title":"Comput Linguistics"},{"key":"ref50","first-page":"644","article-title":"A simple, fast, and effective reparameterization of ibm model 2","author":"dyer","year":"0","journal-title":"Proc Conf North Amer Chapter Assoc Comput Linguistics Human Lang Technologies"},{"key":"ref51","first-page":"3093","article-title":"Neural machine translation with supervised attention","author":"liu","year":"0","journal-title":"Proc COLING 26th Int Conf Comput Linguistics Proc Conf Tech Papers"},{"key":"ref54","first-page":"5926","article-title":"Mass: Masked sequence to sequence pre-training for language generation","author":"song","year":"0","journal-title":"Proceedings 36th Int Conf Mach Learn"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-1202"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1249"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W18-6318"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/E17-3017"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-1141"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-1119"},{"key":"ref13","first-page":"449","article-title":"Code-switching for enhancing nmt with pre-specified translation","volume":"1","author":"song","year":"2019","journal-title":"Proc Conf North American Chapter Assoc Comput Linguistics Human Language Technologies"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1294"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W17-4742"},{"key":"ref16","first-page":"82","article-title":"Addressing the rare word problem in neural machine translation","volume":"27","author":"luong","year":"2014","journal-title":"Bulletin Univ Agricultural Sci Veterinary Medicine Cluj-Napoca Veterinary Medicine"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1124"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P16-1008"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P16-1154"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1179"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1162\/coli.2007.33.2.201"},{"key":"ref6","first-page":"1243","article-title":"Convolutional sequence to sequence learning","author":"gehring","year":"0","journal-title":"Proc 34th Int Conf Mach Learn -Volume 70"},{"key":"ref5","article-title":"Neural machine translation by jointly learning to align and translate","author":"bahdanau","year":"2015","journal-title":"Proc 3rd Int Conf Learn Representations"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1162"},{"key":"ref7","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"0","journal-title":"Proc Adv Neural Inf Process Syst Annu Conf Neural Inf Process Syst"},{"key":"ref49","first-page":"1019","article-title":"A theoretically grounded application of dropout in recurrent neural networks","author":"gal","year":"0","journal-title":"Proc Advances Neural Inf Process Syst"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W17-4716"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1145\/3065386"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W16-2316"},{"key":"ref47","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"0","journal-title":"Proc 3rd Int Conf Learn Representations"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1580"},{"key":"ref41","first-page":"14 014","article-title":"Are sixteen heads really better than one?","author":"michel","year":"0","journal-title":"Proc Adv Neural Inf Process Syst Annu Conf Neural Inf Process Syst"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.3115\/1075218.1075274"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-4009"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/8938144\/09103090.pdf?arnumber=9103090","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T17:31:20Z","timestamp":1651080680000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9103090\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"references-count":54,"URL":"https:\/\/doi.org\/10.1109\/taslp.2020.2998278","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"type":"print","value":"2329-9290"},{"type":"electronic","value":"2329-9304"}],"subject":[],"published":{"date-parts":[[2020]]}}}