{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T18:30:28Z","timestamp":1730226628280,"version":"3.28.0"},"reference-count":16,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,11,18]],"date-time":"2023-11-18T00:00:00Z","timestamp":1700265600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,11,18]],"date-time":"2023-11-18T00:00:00Z","timestamp":1700265600000},"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":[[2023,11,18]]},"DOI":"10.1109\/ialp61005.2023.10336991","type":"proceedings-article","created":{"date-parts":[[2023,12,12]],"date-time":"2023-12-12T18:34:31Z","timestamp":1702406071000},"page":"90-94","source":"Crossref","is-referenced-by-count":0,"title":["Compression Models via Meta-Learning and Structured Distillation for Named Entity Recognition"],"prefix":"10.1109","author":[{"given":"Qing","family":"Zhang","sequence":"first","affiliation":[{"name":"School of Information Science and Technology, North China University of Technology"}]},{"given":"Zhan","family":"Gao","sequence":"additional","affiliation":[{"name":"School of Information Science and Technology, North China University of Technology"}]},{"given":"Mei","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Information Science and Technology, North China University of Technology"}]},{"given":"Jianyong","family":"Duan","sequence":"additional","affiliation":[{"name":"School of Information Science and Technology, North China University of Technology"}]},{"given":"Hao","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Information Science and Technology, North China University of Technology"}]},{"given":"Li","family":"He","sequence":"additional","affiliation":[{"name":"School of Information Science and Technology, North China University of Technology"}]}],"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","first-page":"6000","article-title":"Attention is all you need","volume-title":"Proceedings of the 31st International Conference on Neural Information Processing Systems","author":"Vaswani","year":"2017"},{"key":"ref3","article-title":"Distilling the knowledge in a neural network","author":"Geoffrey","year":"2015","journal-title":"arXiv preprint"},{"key":"ref4","article-title":"Sequence-level knowledge distillation","author":"Yoon","year":"2016","journal-title":"arXiv preprint"},{"journal-title":"arXiv preprint","article-title":"Distilbert, a distilled version of bert: smaller, faster, cheaper and lighter","author":"Sanh","key":"ref5"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.304"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.46"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1139"},{"key":"ref9","first-page":"1877","article-title":"Language models are few-shot learners","author":"Brown","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01139"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3488560.3498437"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.485"},{"key":"ref13","first-page":"282","article-title":"Conditional Random Fields: Probabilistic Models for Segmenting and Labeling Sequence Data","volume-title":"Proceedings of the Eighteenth International Conference on Machine Learning","author":"Lafferty","year":"2001"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.3115\/1119176.1119195"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00454"},{"key":"ref16","first-page":"13292","article-title":"Learning student-friendly teacher networks for knowledge distillation","volume":"34","author":"Park","year":"2021","journal-title":"Advances in neural information processing systems"}],"event":{"name":"2023 International Conference on Asian Language Processing (IALP)","start":{"date-parts":[[2023,11,18]]},"location":"Singapore, Singapore","end":{"date-parts":[[2023,11,20]]}},"container-title":["2023 International Conference on Asian Language Processing (IALP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10336886\/10336974\/10336991.pdf?arnumber=10336991","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,12]],"date-time":"2024-01-12T01:47:53Z","timestamp":1705024073000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10336991\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,11,18]]},"references-count":16,"URL":"https:\/\/doi.org\/10.1109\/ialp61005.2023.10336991","relation":{},"subject":[],"published":{"date-parts":[[2023,11,18]]}}}