{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T19:23:27Z","timestamp":1740165807085,"version":"3.37.3"},"reference-count":49,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"10","license":[{"start":{"date-parts":[[2020,10,1]],"date-time":"2020-10-01T00:00:00Z","timestamp":1601510400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,10,1]],"date-time":"2020-10-01T00:00:00Z","timestamp":1601510400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,10,1]],"date-time":"2020-10-01T00:00:00Z","timestamp":1601510400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Key Research and Development Program of China","award":["2017YFB1400603"]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Neural Netw. Learning Syst."],"published-print":{"date-parts":[[2020,10]]},"DOI":"10.1109\/tnnls.2019.2947563","type":"journal-article","created":{"date-parts":[[2019,12,5]],"date-time":"2019-12-05T21:01:59Z","timestamp":1575579719000},"page":"3932-3946","source":"Crossref","is-referenced-by-count":14,"title":["Major\u2013Minor Long Short-Term Memory for Word-Level Language Model"],"prefix":"10.1109","volume":"31","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0917-3541","authenticated-orcid":false,"given":"Kai","family":"Shuang","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4595-0881","authenticated-orcid":false,"given":"Rui","family":"Li","sequence":"additional","affiliation":[]},{"given":"Mengyu","family":"Gu","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2197-8126","authenticated-orcid":false,"given":"Jonathan","family":"Loo","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4266-7527","authenticated-orcid":false,"given":"Sen","family":"Su","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.21236\/ADA273556"},{"key":"ref38","article-title":"Dynamic evaluation of neural sequence models","author":"krause","year":"2017","journal-title":"arXiv 1709 07432"},{"key":"ref33","article-title":"Factorization tricks for LSTM networks","author":"kuchaiev","year":"2017","journal-title":"arXiv 1703 10722"},{"key":"ref32","article-title":"On the state of the art of evaluation in neural language models","author":"melis","year":"2017","journal-title":"arXiv 1707 05589"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.243"},{"key":"ref30","article-title":"Recurrent highway networks","author":"zilly","year":"2016","journal-title":"arXiv 1607 03474"},{"key":"ref37","article-title":"Improving neural language models with a continuous cache","author":"grave","year":"2016","journal-title":"arXiv 1612 04426"},{"key":"ref36","article-title":"Pointer sentinel mixture models","author":"merity","year":"2016","journal-title":"arXiv 1609 07843"},{"key":"ref35","article-title":"Neural architecture search with reinforcement learning","author":"zoph","year":"2016","journal-title":"arXiv 1611 01578"},{"key":"ref34","article-title":"Skip connections eliminate singularities","author":"orhan","year":"2017","journal-title":"arXiv 1701 09175"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-49430-8_11"},{"journal-title":"Automatic Speech Recognition?A Deep Learning Approach","year":"2014","author":"yu","key":"ref2"},{"journal-title":"Statistical machine translation","year":"2010","author":"koehn","key":"ref1"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1995.479394"},{"key":"ref22","first-page":"1137","article-title":"A neural probabilistic language model","volume":"3","author":"bengio","year":"2003","journal-title":"J Mach Learn Res"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1006\/csla.1999.0128"},{"key":"ref24","article-title":"Exploring the limits of language modeling","author":"jozefowicz","year":"2016","journal-title":"arXiv 1602 02410"},{"key":"ref23","first-page":"1","article-title":"Recurrent neural network based language model","author":"mikolov","year":"2010","journal-title":"Proc 11th Annu Conf Int Speech Commun Assoc"},{"journal-title":"Pattern Recognition and Neural Networks","year":"2007","author":"ripley","key":"ref26"},{"key":"ref25","article-title":"Fraternal dropout","author":"zolna","year":"2017","journal-title":"arXiv 1711 00066"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2012.6424228"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33013159"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511815829"},{"key":"ref12","article-title":"Breaking the Softmax bottleneck: A high-rank RNN language model","author":"yang","year":"2017","journal-title":"arXiv 1711 03953"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref14","article-title":"Recurrent neural network regularization","author":"zaremba","year":"2014","journal-title":"arXiv 1409 2329"},{"key":"ref15","first-page":"1019","article-title":"A theoretically grounded application of dropout in recurrent neural networks","author":"gal","year":"2016","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref16","article-title":"Tying word vectors and word classifiers: A loss framework for language modeling","author":"inan","year":"2016","journal-title":"arXiv 1611 01462"},{"key":"ref17","first-page":"2741","article-title":"Character-aware neural language models","author":"kim","year":"2016","journal-title":"Proc AAAI"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-1137"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D17-1199"},{"key":"ref4","article-title":"Using the output embedding to improve language models","author":"press","year":"2016","journal-title":"arXiv 1608 05859"},{"key":"ref3","first-page":"1899","article-title":"Compositional morphology for word representations and language modelling","author":"botha","year":"2014","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref6","article-title":"Regularizing and optimizing LSTM language models","author":"merity","year":"2017","journal-title":"arXiv 1708 02182"},{"key":"ref5","article-title":"Learning to generate reviews and discovering sentiment","author":"radford","year":"2017","journal-title":"arXiv 1704 01444"},{"key":"ref8","first-page":"933","article-title":"Language modeling with gated convolutional networks","author":"dauphin","year":"2017","journal-title":"Proc 34th Int Conf Mach Learn"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1031"},{"key":"ref49","first-page":"311","article-title":"BLEU: A method for automatic evaluation of machine translation","author":"papineni","year":"2002","journal-title":"Proc Annual Meeting of the Assoc Computational Linguistics"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1123"},{"key":"ref46","article-title":"Improving neural networks by preventing co-adaptation of feature detectors","author":"hinton","year":"2012","journal-title":"arXiv 1207 0580"},{"key":"ref45","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2014","journal-title":"arXiv 1412 6980"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D17-1151"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D15-1166"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1162\/neco_a_01017"},{"key":"ref41","article-title":"Generating sequences with recurrent neural networks","author":"graves","year":"2013","journal-title":"arXiv 1308 0850 [cs]"},{"key":"ref44","first-page":"1058","article-title":"Regularization of neural networks using dropconnect","author":"wan","year":"2013","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref43","article-title":"Bayesian recurrent neural networks","author":"fortunato","year":"2017","journal-title":"arXiv 1704 02798"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/5962385\/9212662\/08924934.pdf?arnumber=8924934","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T17:19:37Z","timestamp":1651079977000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8924934\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,10]]},"references-count":49,"journal-issue":{"issue":"10"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2019.2947563","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"type":"print","value":"2162-237X"},{"type":"electronic","value":"2162-2388"}],"subject":[],"published":{"date-parts":[[2020,10]]}}}