{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,19]],"date-time":"2026-06-19T16:05:37Z","timestamp":1781885137902,"version":"3.54.5"},"reference-count":54,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2021,2,1]],"date-time":"2021-02-01T00:00:00Z","timestamp":1612137600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,2,1]],"date-time":"2021-02-01T00:00:00Z","timestamp":1612137600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,2,1]],"date-time":"2021-02-01T00:00:00Z","timestamp":1612137600000},"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":["IEEE Trans. Visual. Comput. Graphics"],"published-print":{"date-parts":[[2021,2]]},"DOI":"10.1109\/tvcg.2020.3028976","type":"journal-article","created":{"date-parts":[[2020,10,14]],"date-time":"2020-10-14T19:27:38Z","timestamp":1602703658000},"page":"1160-1170","source":"Crossref","is-referenced-by-count":101,"title":["Attention Flows: Analyzing and Comparing Attention Mechanisms in Language Models"],"prefix":"10.1109","volume":"27","author":[{"given":"Joseph F.","family":"DeRose","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiayao","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Matthew","family":"Berger","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/VISUAL.2019.8933677"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1334"},{"key":"ref32","article-title":"Roberta: A robustly optimized bert pretraining approach","author":"liu","year":"2019","journal-title":"arXiv preprint arXiv 1907 11634"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2018.2865230"},{"key":"ref30","doi-asserted-by":"crossref","first-page":"91","DOI":"10.1109\/TVCG.2016.2598831","article-title":"Towards better analysis of deep convolutional neural networks","volume":"23","author":"liu","year":"2016","journal-title":"IEEE Transactions on Visualization and Computer Graphics"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/MCG.2019.2919033"},{"key":"ref36","first-page":"13","article-title":"Understanding hidden memories of recurrent neural networks","author":"ming","year":"2017","journal-title":"Proc IEEE Conference on Visual Analytics Science and Technology (VAST)"},{"key":"ref35","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":"ref34","article-title":"Recurrent neural network based language model","author":"mikolov","year":"2010","journal-title":"Eleventh Annual Conference of the International Speech Communication Association"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/3313831.3376590"},{"key":"ref27","article-title":"Sensebert: Driving some sense into bert","author":"levine","year":"2019","journal-title":"arXiv preprint arXiv 1908 00310"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W19-4825"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/IV.2009.108"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/2470654.2470724"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2019.2934659"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00300"},{"key":"ref21","article-title":"exbert: A visual analysis tool to explore learned representations in transformers models","author":"hoover","year":"2019","journal-title":"arXiv preprint arXiv 1910 12731"},{"key":"ref24","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2014","journal-title":"arXiv preprint arXiv 1412 6980"},{"key":"ref23","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v30i1.10362","article-title":"Character-aware neural language models","author":"kim","year":"2016","journal-title":"THIRTIETH AAAI Conference on Artificial Intelligence"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1445"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/PacificVis.2013.6596128"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-3007"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W18-5446"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1139"},{"key":"ref53","article-title":"Cnncomparator: Comparative analytics of convolutional neural networks","author":"zeng","year":"2017","journal-title":"arXiv preprint arXiv 1710 05285"},{"key":"ref52","article-title":"Google's neural machine translation system: Bridging the gap between human and machine translation","author":"wu","year":"2016","journal-title":"arXiv preprint arXiv 1609 09058"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W19-4828"},{"key":"ref11","first-page":"4171","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"devlin","year":"0","journal-title":"Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics Human Language Technologies Volume 1 (Long Pavers)"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-1161"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2019.2934595"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2017.2744199"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1424"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-1044"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3290605.3300809"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2018.2843369"},{"key":"ref4","first-page":"1137","article-title":"A neural probabilistic language model","volume":"3","author":"bengio","year":"2003","journal-title":"Journal of Machine Learning Research"},{"key":"ref3","article-title":"Layer normalization","author":"ba","year":"2016","journal-title":"arXiv preprint arXiv 1607 06450"},{"key":"ref6","article-title":"On identifiability in transformers","author":"brunner","year":"2020","journal-title":"International Conference on Learning Representations"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D15-1075"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1179"},{"key":"ref7","article-title":"Rnnbow: Visualizing learning via backpropagation gradients in recurrent neural networks","author":"cashman","year":"2019","journal-title":"arXiv preprint arXiv 1907 11634"},{"key":"ref49","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3290605.3300460"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2018.2865044"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1282"},{"key":"ref48","first-page":"1823","article-title":"How does bert answer questions? a layer-wise analysis of transformer representations","author":"winter","year":"0","journal-title":"Proceedings of ACM International Conference on Information and Knowledge Management"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2017.2744158"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2017.2744358"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-1202"},{"key":"ref44","article-title":"A primer in bertology: What we know about how bert works","author":"rogers","year":"2020","journal-title":"arXiv preprint arXiv 2002 10381"},{"key":"ref43","first-page":"8592","article-title":"Visualizing and measuring the geometry of bert","author":"reif","year":"2019","journal-title":"Advances in neural information processing systems"}],"container-title":["IEEE Transactions on Visualization and Computer Graphics"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/2945\/9340023\/09224153.pdf?arnumber=9224153","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,11,23]],"date-time":"2022-11-23T08:38:56Z","timestamp":1669192736000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9224153\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,2]]},"references-count":54,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/tvcg.2020.3028976","relation":{},"ISSN":["1077-2626","1941-0506","2160-9306"],"issn-type":[{"value":"1077-2626","type":"print"},{"value":"1941-0506","type":"electronic"},{"value":"2160-9306","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,2]]}}}