{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,22]],"date-time":"2025-12-22T12:52:24Z","timestamp":1766407944295,"version":"3.37.3"},"reference-count":25,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100014188","name":"Ministry of Science and ICT (MSIT), South Korea, under the Information Technology Research Center","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100014188","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Institute of Information & Communications Technology Planning & Evaluation","award":["IITP-2023-RS-2022-00156295"],"award-info":[{"award-number":["IITP-2023-RS-2022-00156295"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2023]]},"DOI":"10.1109\/access.2023.3341512","type":"journal-article","created":{"date-parts":[[2023,12,12]],"date-time":"2023-12-12T18:52:38Z","timestamp":1702407158000},"page":"140559-140568","source":"Crossref","is-referenced-by-count":2,"title":["How Does a Transformer Learn Compression? An Attention Study on Huffman and LZ4"],"prefix":"10.1109","volume":"11","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-3376-9330","authenticated-orcid":false,"given":"Beomseok","family":"Seo","sequence":"first","affiliation":[{"name":"Department of Electronic and Electrical Engineering, Hongik University, Seoul, South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6346-4182","authenticated-orcid":false,"given":"Albert","family":"No","sequence":"additional","affiliation":[{"name":"Department of Electronic and Electrical Engineering, Hongik University, Seoul, South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"author":"Vaswani","key":"ref1","article-title":"Attention is all you need"},{"article-title":"Improving language understanding by generative pre-training","year":"2018","author":"Radford","key":"ref2"},{"author":"Devlin","key":"ref3","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding"},{"key":"ref4","article-title":"LLaMA: Open and efficient foundation language models","author":"Touvron","year":"2023","journal-title":"arXiv:2302.13971"},{"author":"Dosovitskiy","key":"ref5","article-title":"An image is worth 16 \u00d7 16 words: Transformers for image recognition at scale"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/icassp.2018.8462506"},{"key":"ref7","article-title":"Attention interpretability across NLP tasks","author":"Vashishth","year":"2019","journal-title":"arXiv:1909.11218"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W19-4808"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1218"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.387"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.40"},{"author":"Jain","key":"ref12","article-title":"Attention is not explanation"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1002"},{"author":"Pandey","key":"ref14","article-title":"On the interpretability of attention networks"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-44070-0_2"},{"author":"Yun","key":"ref16","article-title":"Are transformers universal approximators of sequence-to-sequence functions?"},{"key":"ref17","article-title":"Transformers are universal predictors","author":"Basu","year":"2023","journal-title":"arXiv:2307.07843"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/jrproc.1952.273898"},{"volume-title":"LZ4 frame format description","year":"2022","author":"Collet","key":"ref19"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/tit.1977.1055714"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/tit.1978.1055934"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/mc.1984.1659158"},{"key":"ref23","first-page":"1","article-title":"Neural machine translation by jointly learning to align and translate","volume-title":"Proc. ICLR","author":"Bahdanau"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D15-1166"},{"author":"Brunner","key":"ref25","article-title":"On identifiability in transformers"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/10005208\/10353923.pdf?arnumber=10353923","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,12]],"date-time":"2024-01-12T20:38:27Z","timestamp":1705091907000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10353923\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":25,"URL":"https:\/\/doi.org\/10.1109\/access.2023.3341512","relation":{},"ISSN":["2169-3536"],"issn-type":[{"type":"electronic","value":"2169-3536"}],"subject":[],"published":{"date-parts":[[2023]]}}}