{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T01:22:51Z","timestamp":1740100971465,"version":"3.37.3"},"reference-count":19,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,7,18]],"date-time":"2022-07-18T00:00:00Z","timestamp":1658102400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,7,18]],"date-time":"2022-07-18T00:00:00Z","timestamp":1658102400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100007225","name":"MOST","doi-asserted-by":"publisher","award":["110-2634-F-005-006"],"award-info":[{"award-number":["110-2634-F-005-006"]}],"id":[{"id":"10.13039\/100007225","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,7,18]]},"DOI":"10.1109\/ijcnn55064.2022.9891931","type":"proceedings-article","created":{"date-parts":[[2022,9,30]],"date-time":"2022-09-30T19:56:04Z","timestamp":1664567764000},"page":"1-9","source":"Crossref","is-referenced-by-count":0,"title":["Hierarchical Cache Transformer: Dynamic Early Exit for Language Translation"],"prefix":"10.1109","author":[{"given":"Chih-Shuo","family":"Tsai","sequence":"first","affiliation":[{"name":"National Chung Hsing University,Deparment of Computer Science Engineering,Taichung,Taiwan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ying-Hong","family":"Chan","sequence":"additional","affiliation":[{"name":"National Chung Hsing University,Deparment of Computer Science Engineering,Taichung,Taiwan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yao-Chung","family":"Fan","sequence":"additional","affiliation":[{"name":"National Chung Hsing University,Deparment of Computer Science Engineering,Taichung,Taiwan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.204"},{"key":"ref11","article-title":"Bert loses patience: Fast and robust inference with early exit","author":"zhou","year":"2020","journal-title":"ArXiv Preprint"},{"key":"ref12","article-title":"Empirical evaluation of gated recurrent neural networks on sequence modeling","author":"chung","year":"2014","journal-title":"ArXiv Preprint"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref14","article-title":"Tinybert: Distilling bert for natural language understanding","author":"jiao","year":"2019","journal-title":"ArXiv Preprint"},{"key":"ref15","article-title":"Distilbert, a distilled version of bert: smaller, faster, cheaper and lighter","author":"sanh","year":"2019","journal-title":"ArXiv Preprint"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W16-2301"},{"key":"ref17","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2014","journal-title":"ArXiv Preprint"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref19","first-page":"74","article-title":"Rouge: A package for automatic evaluation of summaries","author":"lin","year":"2004","journal-title":"Text Summarization Branches Out"},{"key":"ref4","article-title":"Distilling the knowledge in a neural network","author":"hinton","year":"2015","journal-title":"ArXiv Preprint"},{"key":"ref3","article-title":"Compressing deep convolutional networks using vector quantization","author":"gong","year":"2014","journal-title":"ArXiv Preprint"},{"key":"ref6","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"devlin","year":"2018","journal-title":"ArXiv Preprint"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2016.7900006"},{"key":"ref8","article-title":"Bart: Denoising sequence-to-sequence pre-training for natural language generation, translation, and comprehension","author":"lewis","year":"2019","journal-title":"ArXiv Preprint"},{"key":"ref7","first-page":"9","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"radford","year":"2019","journal-title":"OpenAIRE blog"},{"key":"ref2","article-title":"Learning both weights and con-nections for efficient neural networks","author":"han","year":"2015","journal-title":"ArXiv Preprint"},{"key":"ref1","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"ArXiv Preprint"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.537"}],"event":{"name":"2022 International Joint Conference on Neural Networks (IJCNN)","start":{"date-parts":[[2022,7,18]]},"location":"Padua, Italy","end":{"date-parts":[[2022,7,23]]}},"container-title":["2022 International Joint Conference on Neural Networks (IJCNN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9891857\/9889787\/09891931.pdf?arnumber=9891931","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,11,3]],"date-time":"2022-11-03T23:00:21Z","timestamp":1667516421000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9891931\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,7,18]]},"references-count":19,"URL":"https:\/\/doi.org\/10.1109\/ijcnn55064.2022.9891931","relation":{},"subject":[],"published":{"date-parts":[[2022,7,18]]}}}