{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,22]],"date-time":"2024-10-22T23:10:41Z","timestamp":1729638641744,"version":"3.28.0"},"reference-count":36,"publisher":"IEEE","license":[{"start":{"date-parts":[[2019,7,1]],"date-time":"2019-07-01T00:00:00Z","timestamp":1561939200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,7,1]],"date-time":"2019-07-01T00:00:00Z","timestamp":1561939200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,7,1]],"date-time":"2019-07-01T00:00:00Z","timestamp":1561939200000},"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":[[2019,7]]},"DOI":"10.1109\/ijcnn.2019.8852398","type":"proceedings-article","created":{"date-parts":[[2019,10,1]],"date-time":"2019-10-01T03:44:32Z","timestamp":1569901472000},"page":"1-7","source":"Crossref","is-referenced-by-count":1,"title":["Improving Universal Language Model Fine-Tuning using Attention Mechanism"],"prefix":"10.1109","author":[{"given":"Flavio A. O.","family":"Santos","sequence":"first","affiliation":[]},{"given":"K.L.","family":"Ponce-Guevara","sequence":"additional","affiliation":[]},{"given":"David","family":"Macedo","sequence":"additional","affiliation":[]},{"given":"Cleber","family":"Zanchettin","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"article-title":"Supervised and semi-supervised text categorization using lstm for region embeddings","year":"2016","author":"johnson","key":"ref33"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-1161"},{"key":"ref31","first-page":"137","article-title":"A focused backpropagation algorithm for temporal","author":"mozer","year":"1995","journal-title":"Backpropagation Theory Architectures and Applications"},{"key":"ref30","first-page":"649","article-title":"Character-level convolutional networks for text classification","author":"zhang","year":"2015","journal-title":"Advances in neural information processing systems"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-1052"},{"article-title":"Text classification improved by integrating bidirectional lstm with two-dimensional max pooling","year":"2016","author":"zhou","key":"ref35"},{"article-title":"Adversarial training methods for semi-supervised text classification","year":"2016","author":"miyato","key":"ref34"},{"article-title":"Pointer sentinel mixture models","year":"2016","author":"merity","key":"ref10"},{"key":"ref11","first-page":"577","article-title":"Attention-based models for speech recognition","author":"chorowski","year":"2015","journal-title":"Advances in neural information processing systems"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1031"},{"key":"ref14","first-page":"2048","article-title":"Show, attend and tell: Neural image caption generation with visual attention","author":"xu","year":"2015","journal-title":"International Conference on Machine Learning"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref16","first-page":"647","article-title":"Decaf: A deep convolutional activation feature for generic visual recognition","author":"donahue","year":"2014","journal-title":"International Conference on Machine Learning"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-68612-7_66"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"},{"article-title":"Gradnorm: Gradient normalization for adaptive loss balancing in deep multitask networks","year":"2017","author":"chen","key":"ref28"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2013.08.015"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/S15-2079"},{"key":"ref3","article-title":"Dealing with information overload when using social media for emergency management: Emerging solutions","author":"hiltz","year":"2013","journal-title":"ISCRAM"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1181"},{"key":"ref29","first-page":"142","article-title":"Learning word vectors for sentiment analysis","author":"maas","year":"2011","journal-title":"Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics Human Language Technologies-Volume 1"},{"key":"ref5","doi-asserted-by":"crossref","first-page":"436","DOI":"10.1038\/nature14539","article-title":"Deep learning","volume":"521","author":"lecun","year":"2015","journal-title":"Nature"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1080\/095400999116340"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/1390156.1390177"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.dss.2010.08.009"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2009.191"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/1531914.1531920"},{"key":"ref20","first-page":"3111","article-title":"Distributed representations of words and phrases and their compositionality","author":"mikolov","year":"2013","journal-title":"Advances in neural information processing systems"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-1194"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00051"},{"article-title":"A joint many-task model: Growing a neural network for multiple nlp tasks","year":"2016","author":"hashimoto","key":"ref24"},{"key":"ref23","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v32i1.12006","article-title":"Empower sequence labeling with task-aware neural language model","author":"liu","year":"2018","journal-title":"Thirty-Second AAAI Conference on Artificial Intelligence"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-2081"},{"key":"ref25","first-page":"6294","article-title":"Learned in translation: Contextualized word vectors","author":"mccann","year":"2017","journal-title":"Advances in neural information processing systems"}],"event":{"name":"2019 International Joint Conference on Neural Networks (IJCNN)","start":{"date-parts":[[2019,7,14]]},"location":"Budapest, Hungary","end":{"date-parts":[[2019,7,19]]}},"container-title":["2019 International Joint Conference on Neural Networks (IJCNN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8840768\/8851681\/08852398.pdf?arnumber=8852398","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,9,21]],"date-time":"2023-09-21T03:18:06Z","timestamp":1695266286000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8852398\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,7]]},"references-count":36,"URL":"https:\/\/doi.org\/10.1109\/ijcnn.2019.8852398","relation":{},"subject":[],"published":{"date-parts":[[2019,7]]}}}