{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,4]],"date-time":"2025-09-04T14:19:41Z","timestamp":1756995581158,"version":"3.32.0"},"reference-count":12,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,12,14]],"date-time":"2024-12-14T00:00:00Z","timestamp":1734134400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,12,14]],"date-time":"2024-12-14T00:00:00Z","timestamp":1734134400000},"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":[[2024,12,14]]},"DOI":"10.1109\/icm63406.2024.10815822","type":"proceedings-article","created":{"date-parts":[[2024,12,31]],"date-time":"2024-12-31T19:25:30Z","timestamp":1735673130000},"page":"1-5","source":"Crossref","is-referenced-by-count":2,"title":["Hardware Accelerator for Bidirectional Encoder Representations from Transformers (BERT)"],"prefix":"10.1109","author":[{"given":"Yiming","family":"Wang","sequence":"first","affiliation":[{"name":"Prodrive Technologies,Dept. of Embedded Computing Systems,Eindhoven,Netherlands"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018","journal-title":"arXiv preprint"},{"key":"ref2","article-title":"Llm-pruner: On the structural pruning of large language models","author":"Ma","year":"2023","journal-title":"Advances in neural information processing systems"},{"key":"ref3","article-title":"Albert: A lite bert for self-supervised learning of language representations","author":"Lan","year":"2019","journal-title":"arXiv preprint"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1441"},{"key":"ref5","first-page":"38087","article-title":"Smoothquant: Accurate and efficient post-training quantization for large language models","volume-title":"International Conference on Machine Learning","author":"Xiao"},{"key":"ref6","article-title":"Omniquant: Omnidirectionally calibrated quantization for large language models","author":"Shao","year":"2023","journal-title":"arXiv preprint"},{"key":"ref7","article-title":"A survey on transformer compression","author":"Tang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00413"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3079856.3080246"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/LCA.2020.2979965"},{"key":"ref11","article-title":"Layer normalization","author":"Ba","year":"2016","journal-title":"arXiv preprint"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/SOCC49529.2020.9524802"}],"event":{"name":"2024 International Conference on Microelectronics (ICM)","start":{"date-parts":[[2024,12,14]]},"location":"Doha, Qatar","end":{"date-parts":[[2024,12,17]]}},"container-title":["2024 International Conference on Microelectronics (ICM)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10815720\/10815705\/10815822.pdf?arnumber=10815822","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T07:46:22Z","timestamp":1735717582000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10815822\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,14]]},"references-count":12,"URL":"https:\/\/doi.org\/10.1109\/icm63406.2024.10815822","relation":{},"subject":[],"published":{"date-parts":[[2024,12,14]]}}}