{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T19:37:40Z","timestamp":1730230660412,"version":"3.28.0"},"reference-count":39,"publisher":"IEEE","license":[{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"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":[],"published-print":{"date-parts":[[2020,5]]},"DOI":"10.1109\/icassp40776.2020.9054324","type":"proceedings-article","created":{"date-parts":[[2020,4,9]],"date-time":"2020-04-09T20:21:13Z","timestamp":1586463673000},"page":"6154-6158","source":"Crossref","is-referenced-by-count":0,"title":["How Much Self-Attention Do We Need\u0192 Trading Attention for Feed-Forward Layers"],"prefix":"10.1109","author":[{"given":"Kazuki","family":"Irie","sequence":"first","affiliation":[]},{"given":"Alexander","family":"Gerstenberger","sequence":"additional","affiliation":[]},{"given":"Ralf","family":"Schluter","sequence":"additional","affiliation":[]},{"given":"Hermann","family":"Ney","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"first-page":"5998","volume-title":"Proc. NIPS","author":"Vaswani","key":"ref1"},{"volume-title":"Language models are unsupervised multitask learners","year":"2019","author":"Radford","key":"ref2"},{"key":"ref3","first-page":"4171","article-title":"BERT: pre-training of deep bidirectional transformers for language understanding","volume-title":"Proc. NAACL-HLT","author":"Devlin"},{"key":"ref4","article-title":"Generating wikipedia by sum-marizing long sequences","author":"Liu","year":"2018","journal-title":"ICLR, Vancouver, Canada"},{"article-title":"Adaptive input representations for neural language modeling","volume-title":"ICLR","author":"Baevski","key":"ref5"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33013159"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1285"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2019-1819"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2019-2225"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2014-167"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4615-3210-1"},{"key":"ref12","first-page":"137","article-title":"On using monolingual corpora in neural machine translation","volume":"45","author":"G\u00fcl\u00e7ehre","year":"2017","journal-title":"Computer Speech & Language"},{"key":"ref13","first-page":"3935","article-title":"Enhancing the TED-LIUM corpus with selected data for language modeling and more TED talks","author":"Rousseau","year":"2014","journal-title":"LREC"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.5555\/3026877.3026899"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-4022"},{"key":"ref16","article-title":"ALBERT: A lite bert for self-supervised learning of language representations","author":"Lan","year":"2020","journal-title":"ICLR, Addis Ababa, Ethiopia"},{"key":"ref17","article-title":"Reformer: The efficient transformer","author":"Kitaev","year":"2020","journal-title":"ICLR, Addis Ababa, Ethiopia"},{"key":"ref18","article-title":"Compressive transformers for long-range sequence modelling","author":"Rae","year":"2020","journal-title":"ICLR, Addis Ababa, Ethiopia"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2017.8268931"},{"article-title":"Large memory layers with product keys","volume-title":"Proc. NeurIPS","author":"Lample","key":"ref20"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/p18-1167"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1008"},{"article-title":"Distilling the knowledge in a neural network","volume-title":"NIPS Deep Learning and Representation Learning Workshop","author":"Hinton","key":"ref23"},{"key":"ref24","first-page":"2654","article-title":"Do deep nets really need to be deep\u0192","volume-title":"Proc. NIPS","volume":"27","author":"Ba"},{"article-title":"Domain robust, fast, and compact neural language models for automatic speech recognition","volume-title":"ICASSP","author":"Gerstenberger","key":"ref25"},{"key":"ref26","article-title":"Layer normalization","author":"Ba","year":"2016","journal-title":"Preprint arXiv:1607.06450"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_38"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003788"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1995.479394"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1006\/csla.1999.0128"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2011-250"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2010-525"},{"key":"ref34","first-page":"297","article-title":"Noise-contrastive estimation: A new estimation principle for unnormalized statistical models","volume-title":"Proc. AISTATS","author":"Gutmann"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/P14-1129"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461743"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053573"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2015-513"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/P15-2081"}],"event":{"name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2020,5,4]]},"location":"Barcelona, Spain","end":{"date-parts":[[2020,5,8]]}},"container-title":["ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9040208\/9052899\/09054324.pdf?arnumber=9054324","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,7,18]],"date-time":"2024-07-18T06:10:13Z","timestamp":1721283013000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9054324\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,5]]},"references-count":39,"URL":"https:\/\/doi.org\/10.1109\/icassp40776.2020.9054324","relation":{},"subject":[],"published":{"date-parts":[[2020,5]]}}}