{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T19:48:05Z","timestamp":1730231285592,"version":"3.28.0"},"reference-count":19,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"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":[[2023,6,4]]},"DOI":"10.1109\/icassp49357.2023.10095944","type":"proceedings-article","created":{"date-parts":[[2023,5,5]],"date-time":"2023-05-05T17:28:30Z","timestamp":1683307710000},"page":"1-5","source":"Crossref","is-referenced-by-count":0,"title":["Skillnet-NLG: General-Purpose Natural Language Generation with a Sparsely Activated Approach"],"prefix":"10.1109","author":[{"given":"Junwei","family":"Liao","sequence":"first","affiliation":[{"name":"University of Electronic Science and Technology of China"}]},{"given":"Duyu","family":"Tang","sequence":"additional","affiliation":[{"name":"Tencent AI Lab"}]},{"given":"Fan","family":"Zhang","sequence":"additional","affiliation":[{"name":"Tencent AI Lab"}]},{"given":"Shuming","family":"Shi","sequence":"additional","affiliation":[{"name":"Tencent AI Lab"}]}],"member":"263","reference":[{"doi-asserted-by":"publisher","key":"ref13","DOI":"10.24963\/ijcai.2018\/567"},{"doi-asserted-by":"publisher","key":"ref12","DOI":"10.1007\/978-3-319-99501-4_41"},{"year":"2020","author":"wolf","article-title":"Huggingface’s transformers: State-of-the-art natural language processing","key":"ref15"},{"year":"2021","author":"guan","article-title":"Lot: A benchmark for evaluating chinese long text understanding and generation","key":"ref14"},{"doi-asserted-by":"publisher","key":"ref11","DOI":"10.18653\/v1\/2020.acl-main.635"},{"doi-asserted-by":"publisher","key":"ref10","DOI":"10.18653\/v1\/2020.acl-main.330"},{"doi-asserted-by":"publisher","key":"ref2","DOI":"10.18653\/v1\/P19-1441"},{"key":"ref1","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Proc of NeurIPS"},{"doi-asserted-by":"publisher","key":"ref17","DOI":"10.1162\/tacl_a_00343"},{"key":"ref16","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2015","journal-title":"Proc of ICLR"},{"doi-asserted-by":"publisher","key":"ref19","DOI":"10.18653\/v1\/2020.findings-emnlp.299"},{"doi-asserted-by":"publisher","key":"ref18","DOI":"10.1609\/aaai.v34i01.5476"},{"doi-asserted-by":"publisher","key":"ref8","DOI":"10.18653\/v1\/D15-1229"},{"year":"2020","author":"lepikhin","article-title":"Gshard: Scaling giant models with conditional computation and automatic sharding","key":"ref7"},{"year":"2021","author":"shao","article-title":"Cpt: A pre-trained unbalanced transformer for both chinese language understanding and generation","key":"ref9"},{"doi-asserted-by":"publisher","key":"ref4","DOI":"10.18653\/v1\/2020.acl-main.703"},{"key":"ref3","first-page":"1","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","volume":"21","author":"raffel","year":"2020","journal-title":"J Mach Learn Res"},{"year":"2022","author":"zhang","article-title":"Skillnetnlu: A sparsely activated model for general-purpose natural language understanding","key":"ref6"},{"key":"ref5","article-title":"Introducing pathways: A next-generation ai architecture","author":"dean","year":"2021","journal-title":"Google Blog"}],"event":{"name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2023,6,4]]},"location":"Rhodes Island, Greece","end":{"date-parts":[[2023,6,10]]}},"container-title":["ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10094559\/10094560\/10095944.pdf?arnumber=10095944","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,20]],"date-time":"2023-11-20T19:06:42Z","timestamp":1700507202000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10095944\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,4]]},"references-count":19,"URL":"https:\/\/doi.org\/10.1109\/icassp49357.2023.10095944","relation":{},"subject":[],"published":{"date-parts":[[2023,6,4]]}}}