{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,2]],"date-time":"2026-01-02T07:46:54Z","timestamp":1767340014141,"version":"3.37.3"},"reference-count":35,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"8","license":[{"start":{"date-parts":[[2023,8,1]],"date-time":"2023-08-01T00:00:00Z","timestamp":1690848000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,8,1]],"date-time":"2023-08-01T00:00:00Z","timestamp":1690848000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,8,1]],"date-time":"2023-08-01T00:00:00Z","timestamp":1690848000000},"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 Trans. Neural Netw. Learning Syst."],"published-print":{"date-parts":[[2023,8]]},"DOI":"10.1109\/tnnls.2021.3114188","type":"journal-article","created":{"date-parts":[[2021,10,25]],"date-time":"2021-10-25T19:42:25Z","timestamp":1635190945000},"page":"4321-4331","source":"Crossref","is-referenced-by-count":7,"title":["An Empirical Study on Adaptive Inference for Pretrained Language Model"],"prefix":"10.1109","volume":"34","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8023-9913","authenticated-orcid":false,"given":"Weijie","family":"Liu","sequence":"first","affiliation":[{"name":"Technology and Engineering Group (TEG), Tencent, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xin","family":"Zhao","sequence":"additional","affiliation":[{"name":"School of Information, Renmin University of China, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhe","family":"Zhao","sequence":"additional","affiliation":[{"name":"Technology and Engineering Group (TEG), Tencent, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qi","family":"Ju","sequence":"additional","affiliation":[{"name":"Technology and Engineering Group (TEG), Tencent, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xuefeng","family":"Yang","sequence":"additional","affiliation":[{"name":"Technology and Engineering Group (TEG), Tencent, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6769-2695","authenticated-orcid":false,"given":"Wei","family":"Lu","sequence":"additional","affiliation":[{"name":"School of Information, Renmin University of China, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.204"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/JAS.2020.1003243"},{"key":"ref12","article-title":"Efficient relational sentence ordering network","author":"li","year":"2021","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TCSS.2020.3033302"},{"key":"ref15","article-title":"ALBERT: A lite bert for self-supervised learning of language representations","author":"lan","year":"2020","journal-title":"Proc Int Conf Learn Represent (ICLR)"},{"key":"ref14","article-title":"BERT loses patience: Fast and robust inference with early exit","author":"zhou","year":"2020","journal-title":"Proc Conf Empirical Methods Natural Lang Process (EMNLP)"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICMLA.2017.0-134"},{"key":"ref30","article-title":"ADAM: A method for stochastic optimization","author":"kingma","year":"2015","journal-title":"Proc Int Conf for Learn Represent (ICLR)"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.195"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-1408"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.findings-emnlp.372"},{"key":"ref32","article-title":"Dynamic embedding projection-gated convolutional neural networks for text classification","author":"tan","year":"2021","journal-title":"IEEE Trans Neural Netw Learn Syst"},{"key":"ref2","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"devlin","year":"2019","journal-title":"Proc Conf North Amer Chapter Assoc Comput Linguistics (NAACL)"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.537"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TCSS.2020.3014128"},{"key":"ref16","doi-asserted-by":"crossref","first-page":"1872","DOI":"10.1007\/s11431-020-1647-3","article-title":"Pre-trained models for natural language processing: A survey","volume":"63","author":"xipeng","year":"2020","journal-title":"Sci China Technol Sci"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6428"},{"key":"ref18","first-page":"296","article-title":"KoELMo: Deep Contextualized word representations for Korean","author":"hong","year":"2018","journal-title":"Proc Annu Conf Hum Lang Technol"},{"key":"ref24","article-title":"Depth-adaptive transformer","author":"elbayad","year":"2020","journal-title":"Proc Int Conf Learn Represent (ICLR)"},{"key":"ref23","article-title":"Adaptive neural networks for efficient inference","author":"bolukbasi","year":"2017","journal-title":"arXiv 1702 07811"},{"key":"ref26","article-title":"FitNets: Hints for thin deep nets","author":"romero","year":"2014","journal-title":"arXiv 1412 6550"},{"key":"ref25","first-page":"2790","article-title":"Parameter-efficient transfer learning for NLP","author":"houlsby","year":"2019","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref20","first-page":"933","article-title":"Language modeling with gated convolutional networks","author":"dauphin","year":"2017","journal-title":"Proc Int Conf Mach Learn (ICML)"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2016.7900006"},{"key":"ref21","first-page":"1","article-title":"Preventing gradient explosions in gated recurrent units","author":"kanai","year":"2017","journal-title":"Proc 31st Int Conf Neural Inf Process Syst (NeurIPS)"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-3041"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1441"},{"key":"ref29","article-title":"AMBERT: A pre-trained language model with multi-grained tokenization","author":"zhang","year":"2020","journal-title":"arXiv 2008 11869"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1374"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1445"},{"key":"ref9","article-title":"DistilBERT, a distilled version of bert: Smaller, faster, cheaper and lighter","author":"sanh","year":"2019","journal-title":"Proc NeurIPS EMC2 Workshop"},{"key":"ref4","article-title":"RoBERTa: A robustly optimized BERT pretraining approach","author":"liu","year":"2019","journal-title":"arXiv 1907 11692"},{"article-title":"Improving language understanding by generative pre-training","year":"2018","author":"radford","key":"ref3"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.coling-main.419"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W18-5446"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/5962385\/10208115\/09585316.pdf?arnumber=9585316","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,21]],"date-time":"2023-08-21T18:01:26Z","timestamp":1692640886000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9585316\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,8]]},"references-count":35,"journal-issue":{"issue":"8"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2021.3114188","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"type":"print","value":"2162-237X"},{"type":"electronic","value":"2162-2388"}],"subject":[],"published":{"date-parts":[[2023,8]]}}}