{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T01:09:52Z","timestamp":1740100192555,"version":"3.37.3"},"reference-count":33,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,7,18]],"date-time":"2021-07-18T00:00:00Z","timestamp":1626566400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,7,18]],"date-time":"2021-07-18T00:00:00Z","timestamp":1626566400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,7,18]],"date-time":"2021-07-18T00:00:00Z","timestamp":1626566400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100004442","name":"National Science Centre (Poland)","doi-asserted-by":"publisher","award":["2019\/35\/N\/ST6\/02125"],"award-info":[{"award-number":["2019\/35\/N\/ST6\/02125"]}],"id":[{"id":"10.13039\/501100004442","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,7,18]]},"DOI":"10.1109\/ijcnn52387.2021.9533990","type":"proceedings-article","created":{"date-parts":[[2021,9,20]],"date-time":"2021-09-20T21:27:41Z","timestamp":1632173261000},"page":"1-6","source":"Crossref","is-referenced-by-count":1,"title":["Multitask Learning Using BERT with Task-Embedded Attention"],"prefix":"10.1109","author":[{"given":"Lukasz","family":"Maziarka","sequence":"first","affiliation":[]},{"given":"Tomasz","family":"Danel","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref33","article-title":"Parameter-efficient transfer learning for nlp","author":"houlsby","year":"2019","journal-title":"ArXiv Preprint"},{"key":"ref32","article-title":"The winograd schema challenge","author":"levesque","year":"0","journal-title":"Thirteenth International Conference on the Principles of Knowledge Representation and Reasoning"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1264"},{"key":"ref30","article-title":"A broad-coverage challenge corpus for sentence understanding through inference","author":"williams","year":"2017","journal-title":"ArXiv Preprint"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-1202"},{"journal-title":"Improving language understanding by generative pre-training","year":"2018","author":"radford","key":"ref11"},{"key":"ref12","article-title":"Roberta: A robustly optimized bert pretraining approach","author":"liu","year":"2019","journal-title":"ArXiv Preprint"},{"key":"ref13","first-page":"5753","article-title":"Xlnet: Generalized autoregressive pretraining for language understanding","author":"yang","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref14","article-title":"Electra: Pretraining text encoders as discriminators rather than generators","author":"clark","year":"2020","journal-title":"ArXiv Preprint"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/N15-1092"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1441"},{"journal-title":"Bert and pals Projected attention layers for efficient adaptation in multi-task learning","year":"2019","author":"stickland","key":"ref17"},{"key":"ref18","article-title":"Adapter-fusion: Non-destructive task composition for transfer learning","author":"pfeiffer","year":"2020","journal-title":"ArXiv Preprint"},{"journal-title":"Bridging nonlinearities and stochastic regularizers with Gaussian error linear units","year":"2016","author":"hendrycks","key":"ref19"},{"journal-title":"Quora Question Pairs?Kaggle","year":"2018","author":"chen","key":"ref28"},{"key":"ref4","article-title":"Neural machine translation by jointly learning to align and translate","author":"bahdanau","year":"2014","journal-title":"ArXiv Preprint"},{"key":"ref27","article-title":"Automatically constructing a corpus of sentential paraphrases","author":"dolan","year":"0","journal-title":"Proceedings of the Third International Workshop on Paraphrasing (IWP2005)"},{"key":"ref3","first-page":"3104","article-title":"Sequence to sequence learning with neural networks","author":"sutskever","year":"2014","journal-title":"Advances in neural information processing systems"},{"key":"ref6","article-title":"Image transformer","author":"parmar","year":"2018","journal-title":"ArXiv Preprint"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/S17-2001"},{"key":"ref5","article-title":"Convo-lutional sequence to sequence learning","author":"gehring","year":"2017","journal-title":"ArXiv Preprint"},{"key":"ref8","article-title":"Molecule attention transformer","author":"maziarka","year":"2020","journal-title":"ArXiv Preprint"},{"key":"ref7","article-title":"Stand-alone self-attention in vision models","author":"ramachandran","year":"2019","journal-title":"ArXiv Preprint"},{"journal-title":"Attention is all you need","year":"2017","author":"vaswani","key":"ref2"},{"key":"ref9","article-title":"Music transformer","author":"huang","year":"2018","journal-title":"ArXiv Preprint"},{"journal-title":"BERT Pre-training of deep bidirectional transformers for language understanding","year":"2018","author":"devlin","key":"ref1"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W19-4828"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref21","article-title":"Layer normalization","author":"ba","year":"2016","journal-title":"ArXiv Preprint"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W18-5446"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33016949"},{"key":"ref26","first-page":"1631","article-title":"Recursive deep models for semantic compositionality over a sentiment treebank","author":"socher","year":"0","journal-title":"Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00290"}],"event":{"name":"2021 International Joint Conference on Neural Networks (IJCNN)","start":{"date-parts":[[2021,7,18]]},"location":"Shenzhen, China","end":{"date-parts":[[2021,7,22]]}},"container-title":["2021 International Joint Conference on Neural Networks (IJCNN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9533266\/9533267\/09533990.pdf?arnumber=9533990","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T15:46:18Z","timestamp":1652197578000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9533990\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,7,18]]},"references-count":33,"URL":"https:\/\/doi.org\/10.1109\/ijcnn52387.2021.9533990","relation":{},"subject":[],"published":{"date-parts":[[2021,7,18]]}}}