{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T04:51:09Z","timestamp":1782881469725,"version":"3.54.5"},"reference-count":40,"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"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,7,18]]},"DOI":"10.1109\/ijcnn52387.2021.9533563","type":"proceedings-article","created":{"date-parts":[[2021,9,20]],"date-time":"2021-09-20T21:27:41Z","timestamp":1632173261000},"page":"1-8","source":"Crossref","is-referenced-by-count":6,"title":["Of Non-Linearity and Commutativity in BERT"],"prefix":"10.1109","author":[{"given":"Sumu","family":"Zhao","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Damian","family":"Pascual","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Gino","family":"Brunner","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Roger","family":"Wattenhofer","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","author":"yang","year":"2019","journal-title":"XLNet Generalized Autoregressive Pretraining for Language Understanding"},{"key":"ref38","article-title":"Lite transformer with long-short range attention","author":"wu","year":"2020","journal-title":"8th International Conference on Learning Representations ICLR 2020"},{"key":"ref33","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref32","article-title":"What do you learn from context? probing for sentence structure in contextualized word representations","author":"tenney","year":"0","journal-title":"International Conference on Learning Representations"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1452"},{"key":"ref30","article-title":"Distilbert, a distilled version of bert: smaller, faster, cheaper and lighter","author":"sanh","year":"2019","journal-title":"ArXiv Preprint"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.422"},{"key":"ref36","article-title":"Transformers: State-of-the-art natural language processing","author":"wolf","year":"2019","journal-title":"ArXiv Preprint"},{"key":"ref35","article-title":"GLUE: A multi-task benchmark and analysis platform for natural language understanding","author":"wang","year":"2019","journal-title":"7th International Conference on Learning Representations ICLR 2019"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1580"},{"key":"ref10","article-title":"Gaussian error linear units (gelus)","author":"hendrycks","year":"2016","journal-title":"ArXiv Preprint"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.11"},{"key":"ref11","article-title":"Do attention heads in bert track syntactic dependencies?","author":"htut","year":"2019","journal-title":"ArXiv Preprint"},{"key":"ref12","first-page":"3543","article-title":"Attention is not explanation","author":"jain","year":"0","journal-title":"Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1356"},{"key":"ref14","article-title":"Cross-lingual ability of multilingual bert: An empirical study","author":"karthikeyan","year":"0","journal-title":"International Conference on Learning Representations"},{"key":"ref15","article-title":"Reformer: The efficient transformer","author":"kitaev","year":"2020","journal-title":"ArXiv Preprint"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1445"},{"key":"ref17","article-title":"Albert: A lite bert for self-supervised learning of language representations","author":"lan","year":"0","journal-title":"International Conference on Learning Representations"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W19-4825"},{"key":"ref19","article-title":"Roberta: A robustly optimized bert pretraining approach","author":"liu","year":"2019","journal-title":"ArXiv Preprint"},{"key":"ref28","article-title":"A primer in bertology: What we know about how bert works","author":"rogers","year":"2020","journal-title":"ArXiv Preprint"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W19-4828"},{"key":"ref27","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","author":"raffel","year":"2019","journal-title":"ArXiv Preprint"},{"key":"ref3","article-title":"On identifiability in transformers","author":"brunner","year":"0","journal-title":"International Conference on Learning Representations"},{"key":"ref6","first-page":"4171","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","volume":"1","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"},{"key":"ref29","article-title":"Poor man's bert: Smaller and faster transformer models","author":"sajjad","year":"2020","journal-title":"ArXiv Preprint"},{"key":"ref5","article-title":"Universal transformers","author":"dehghani","year":"0","journal-title":"International Conference on Learning Representations"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1006"},{"key":"ref7","first-page":"4865","article-title":"Analyzing individual neurons in pre-trained language models","author":"durrani","year":"0","journal-title":"Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)"},{"key":"ref2","author":"brown","year":"2020","journal-title":"Language models are few-shot learners"},{"key":"ref9","author":"gokaslan","year":"2019","journal-title":"OpenWebText Corpus"},{"key":"ref1","first-page":"690","article-title":"Deep equilibrium models","volume":"32","author":"bai","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref20","first-page":"14014","article-title":"Are sixteen heads really better than one?","author":"michel","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"},{"key":"ref21","article-title":"Telling bert's full story: from local attention to global aggregation","author":"pascual","year":"2020","journal-title":"ArXiv Preprint"},{"key":"ref24","article-title":"Learning to deceive with attention-based explanations","author":"pruthi","year":"2019","journal-title":"ArXiv Preprint"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.270"},{"key":"ref26","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"radford","year":"2019","journal-title":"OpenAIRE blog"},{"key":"ref25","author":"radford","year":"2018","journal-title":"Improving language understanding by generative pre-training"}],"event":{"name":"2021 International Joint Conference on Neural Networks (IJCNN)","location":"Shenzhen, China","start":{"date-parts":[[2021,7,18]]},"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\/09533563.pdf?arnumber=9533563","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T15:46:06Z","timestamp":1652197566000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9533563\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,7,18]]},"references-count":40,"URL":"https:\/\/doi.org\/10.1109\/ijcnn52387.2021.9533563","relation":{},"subject":[],"published":{"date-parts":[[2021,7,18]]}}}