{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,13]],"date-time":"2026-01-13T06:57:50Z","timestamp":1768287470226,"version":"3.49.0"},"reference-count":47,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,12,15]],"date-time":"2021-12-15T00:00:00Z","timestamp":1639526400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,12,15]],"date-time":"2021-12-15T00:00:00Z","timestamp":1639526400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,12,15]],"date-time":"2021-12-15T00:00:00Z","timestamp":1639526400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100009941","name":"Ministry of Defence","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100009941","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,12,15]]},"DOI":"10.1109\/bigdata52589.2021.9671639","type":"proceedings-article","created":{"date-parts":[[2022,1,13]],"date-time":"2022-01-13T20:39:16Z","timestamp":1642106356000},"page":"1193-1203","source":"Crossref","is-referenced-by-count":21,"title":["On Exploring Attention-based Explanation for Transformer Models in Text Classification"],"prefix":"10.1109","author":[{"given":"Shengzhong","family":"Liu","sequence":"first","affiliation":[]},{"given":"Franck","family":"Le","sequence":"additional","affiliation":[]},{"given":"Supriyo","family":"Chakraborty","sequence":"additional","affiliation":[]},{"given":"Tarek","family":"Abdelzaher","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","first-page":"3319","article-title":"Axiomatic attribution for deep networks","author":"sundararajan","year":"2017","journal-title":"Proceedings of the 34th International Conference on Machine Learning-Volume 70"},{"key":"ref38","first-page":"4765","article-title":"A unified approach to interpreting model predictions","author":"lundberg","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref33","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"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.574"},{"key":"ref31","article-title":"Deep inside convolutional networks: Visualising image classification models and saliency maps","author":"simonyan","year":"2014"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-1106"},{"key":"ref37","article-title":"Understanding neural networks through representation erasure","author":"li","year":"2016"},{"key":"ref36","first-page":"818","article-title":"Visualizing and understanding convolutional networks","author":"zeiler","year":"2014","journal-title":"European Conference on Computer Vision"},{"key":"ref35","first-page":"2579","article-title":"Visualizing data using t-sne","volume":"9","author":"maaten","year":"2008","journal-title":"Journal of Machine Learning Research"},{"key":"ref34","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":"ref10","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.432"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.419"},{"key":"ref40","article-title":"Smoothgrad: removing noise by adding noise","author":"smilkov","year":"2017"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.312"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-3007"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.385"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0130140"},{"key":"ref16","doi-asserted-by":"crossref","first-page":"1532","DOI":"10.3115\/v1\/D14-1162","article-title":"Glove: Global vectors for word representation","author":"pennington","year":"2014","journal-title":"Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP)"},{"key":"ref17","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"devlin","year":"2018"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.409"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.386"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1016\/0377-0427(87)90125-7"},{"key":"ref4","article-title":"Neural machine translation by jointly learning to align and translate","author":"bahdanau","year":"2015","journal-title":"3rd International Conference on Learning Representations ICLR 2015"},{"key":"ref27","first-page":"1885","article-title":"Understanding black-box predictions via influence functions","author":"koh","year":"2017","journal-title":"Proceedings of the 34th International Conference on Machine Learning-Volume 70"},{"key":"ref3","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1282"},{"key":"ref29","article-title":"Not just a black box: Learning important features through propagating activation differences","author":"shrikumar","year":"2016"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D17-2021"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1002"},{"key":"ref7","first-page":"3543","article-title":"Attention is not explanation","author":"jain","year":"2019","journal-title":"Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics Human Language Technologies Volume 1 (Long and Short Papers)"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/UIC-ATC.2017.8397411"},{"key":"ref9","article-title":"Attention interpretability across nlp tasks","author":"vashishth","year":"2019"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-019-08987-4"},{"key":"ref20","article-title":"Eraser: A benchmark to evaluate rationalized nlp models","author":"deyoung","year":"2019"},{"key":"ref46","doi-asserted-by":"crossref","first-page":"12963","DOI":"10.1609\/aaai.v35i14.17533","article-title":"Self-attention attribution: Interpreting information interactions inside transformer","volume":"35","author":"hao","year":"2021","journal-title":"Proceedings of the AAAI Conference on Artificial Intelligence"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W19-4828"},{"key":"ref22","article-title":"On the robustness of interpretability methods","author":"alvarez-melis","year":"2018"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W17-5221"},{"key":"ref47","article-title":"Sentence-based model agnostic nlp interpretability","author":"rychener","year":"2020"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/2736277.2741088"},{"key":"ref42","first-page":"3145","article-title":"Learning important features through propagating activation differences","author":"shrikumar","year":"2017","journal-title":"International Conference on Machine Learning"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/3351095.3372836"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-10-0557-2_87"},{"key":"ref26","first-page":"2280","article-title":"Examples are not enough, learn to criticize! criticism for interpretability","author":"kim","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1580"},{"key":"ref25","article-title":"Deep k-nearest neighbors: Towards confident, interpretable and robust deep learning","author":"papernot","year":"2018"},{"key":"ref43","article-title":"Learning to deceive with attention-based explanations","author":"pruthi","year":"2019"}],"event":{"name":"2021 IEEE International Conference on Big Data (Big Data)","location":"Orlando, FL, USA","start":{"date-parts":[[2021,12,15]]},"end":{"date-parts":[[2021,12,18]]}},"container-title":["2021 IEEE International Conference on Big Data (Big Data)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9671263\/9671273\/09671639.pdf?arnumber=9671639","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,22]],"date-time":"2023-01-22T22:06:10Z","timestamp":1674425170000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9671639\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,12,15]]},"references-count":47,"URL":"https:\/\/doi.org\/10.1109\/bigdata52589.2021.9671639","relation":{},"subject":[],"published":{"date-parts":[[2021,12,15]]}}}