{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,16]],"date-time":"2026-04-16T04:51:52Z","timestamp":1776315112363,"version":"3.50.1"},"reference-count":43,"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"}],"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.2020.2995270","type":"journal-article","created":{"date-parts":[[2020,5,18]],"date-time":"2020-05-18T22:42:59Z","timestamp":1589841779000},"page":"1574-1585","source":"Crossref","is-referenced-by-count":21,"title":["Searching Better Architectures for Neural Machine Translation"],"prefix":"10.1109","volume":"28","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0308-955X","authenticated-orcid":false,"given":"Yang","family":"Fan","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fei","family":"Tian","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9823-9033","authenticated-orcid":false,"given":"Yingce","family":"Xia","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tao","family":"Qin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6070-6625","authenticated-orcid":false,"given":"Xiang-Yang","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tie-Yan","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P16-1162"},{"key":"ref38","article-title":"Outrageously large neural networks: The sparsely-gated mixture-of-experts layer","author":"shazeer","year":"2017","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref33","article-title":"Population based training of neural networks","author":"jaderberg","year":"2017"},{"key":"ref32","first-page":"6765","article-title":"Hyperband: A novel bandit-based approach to hyperparameter optimization","volume":"18","author":"li","year":"2017","journal-title":"J Mach Learn Res"},{"key":"ref31","article-title":"A tutorial on bayesian optimization","author":"frazier","year":"2018"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00020"},{"key":"ref37","article-title":"Conditional computation in neural networks for faster models","author":"bengio","year":"2015"},{"key":"ref36","article-title":"Estimating or propagating gradients through stochastic neurons for conditional computation","author":"bengio","year":"2013"},{"key":"ref35","article-title":"SMASH: One-shot model architecture search through hypernetworks","author":"brock","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref34","first-page":"549","article-title":"Understanding and simplifying one-shot architecture search","author":"bender","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref10","first-page":"7816","article-title":"Neural architecture optimization","author":"luo","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref40","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2015","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref11","article-title":"ProxylessNAS: Direct neural architecture search on target task and hardware","author":"cai","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00720"},{"key":"ref13","first-page":"6642","article-title":"DetNAS: Backbone search for object detection","volume":"32","author":"chen","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref14","first-page":"240","article-title":"Non-stochastic best arm identification and hyperparameter optimization","author":"jamieson","year":"0","journal-title":"Proc Artif Intell Statist"},{"key":"ref15","article-title":"Hyperparameter optimization: A spectral approach","author":"hazan","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P16-1009"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/W14-4012"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00105"},{"key":"ref19","article-title":"Pay less attention with lightweight and dynamic convolutions","author":"wu","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref28","first-page":"5877","article-title":"The evolved transformer","author":"so","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"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":"8699","article-title":"Searching for efficient multi-scale architectures for dense image prediction","author":"chen","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref3","article-title":"Neural machine translation by jointly learning to align and translate","author":"bahdanau","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref6","article-title":"Neural machine translation in linear time","author":"kalchbrenner","year":"2016"},{"key":"ref29","first-page":"4790","article-title":"Conditional image generation with pixelcnn decoders","author":"van den oord","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref5","first-page":"1243","article-title":"Convolutional sequence to sequence learning","author":"gehring","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_2"},{"key":"ref7","article-title":"Neural architecture search with reinforcement learning","author":"zoph","year":"2017","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref2","first-page":"3104","article-title":"Sequence to sequence learning with neural networks","author":"sutskever","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref9","article-title":"DARTS: Differentiable architecture search","author":"liu","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref1","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-2074"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-1407"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1008"},{"key":"ref42","article-title":"Hierarchical representations for efficient architecture search","author":"liu","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00907"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1167"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00017"},{"key":"ref43","article-title":"Random search and reproducibility for neural architecture search","author":"li","year":"2019","journal-title":"Proc Conf Uncertainty Artif Intell"},{"key":"ref25","first-page":"4095","article-title":"Efficient neural architecture search via parameter sharing","volume":"80","author":"pham","year":"2018","journal-title":"Proc 35th 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\/09095246.pdf?arnumber=9095246","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\/9095246\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"references-count":43,"URL":"https:\/\/doi.org\/10.1109\/taslp.2020.2995270","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020]]}}}