{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,6]],"date-time":"2026-07-06T15:35:31Z","timestamp":1783352131575,"version":"3.54.6"},"reference-count":49,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/access.2025.3601069","type":"journal-article","created":{"date-parts":[[2025,8,20]],"date-time":"2025-08-20T18:43:26Z","timestamp":1755715406000},"page":"147034-147053","source":"Crossref","is-referenced-by-count":1,"title":["Using Kolmogorov\u2013Arnold Networks in Transformer Model: A Study on Low-Resource Neural Machine Translation"],"prefix":"10.1109","volume":"13","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2149-142X","authenticated-orcid":false,"given":"Bilge Kagan","family":"Yazar","sequence":"first","affiliation":[{"name":"Faculty of Engineering, Ondokuz Mayıs University, Samsun, Türkiye"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1585-0991","authenticated-orcid":false,"given":"Erdal","family":"Kili\u00e7","sequence":"additional","affiliation":[{"name":"Faculty of Engineering, Ondokuz Mayıs University, Samsun, Türkiye"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","first-page":"15","article-title":"Translation","volume-title":"Machine Translation of Languages","author":"Weaver","year":"1955"},{"key":"ref2","first-page":"1","article-title":"A neural probabilistic language model","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Bengio"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.3115\/1273073.1273166"},{"key":"ref4","article-title":"Neural machine translation by jointly learning to align and translate","author":"Bahdanau","year":"2014","journal-title":"arXiv:1409.0473"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref6","article-title":"A survey on recent approaches for natural language processing in low-resource scenarios","author":"Hedderich","year":"2020","journal-title":"arXiv:2010.12309"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3567592"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2023.3336019"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/0893-6080(89)90020-8"},{"key":"ref10","article-title":"KAN: Kolmogorov\u2013Arnold networks","author":"Liu","year":"2024","journal-title":"arXiv:2404.19756"},{"key":"ref11","article-title":"KAN or MLP: A fairer comparison","author":"Yu","year":"2024","journal-title":"arXiv:2407.16674"},{"key":"ref12","first-page":"179","article-title":"On the representation of continuous functions of several variables by superpositions of continuous functions of a smaller number of variables","volume-title":"Proc. USSR Acad. Sci.","volume":"108","author":"Kolmogorov"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2021.01.020"},{"key":"ref14","article-title":"Kolmogorov\u2013Arnold network autoencoders","author":"Moradi","year":"2024","journal-title":"arXiv:2410.02077"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/GCWkshp64532.2024.11100692"},{"key":"ref16","article-title":"A comprehensive survey on Kolmogorov Arnold networks (KAN)","author":"Ji","year":"2024","journal-title":"arXiv:2407.11075"},{"key":"ref17","first-page":"2793","article-title":"Attention is not all you need: Pure attention loses rank doubly exponentially with depth","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Dong"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1016\/j.aiopen.2022.10.001"},{"key":"ref19","volume-title":"Searching for Activation Functions","author":"Ramachandran","year":"2018"},{"key":"ref20","article-title":"GLU variants improve transformer","author":"Shazeer","year":"2020","journal-title":"arXiv:2002.05202"},{"key":"ref21","first-page":"8548","article-title":"Large memory layers with product keys","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Lample"},{"issue":"120","key":"ref22","first-page":"1","article-title":"Switch transformers: Scaling to trillion parameter models with simple and efficient sparsity","volume":"23","author":"Fedus","year":"2021","journal-title":"J. Mach. Learn. Res."},{"key":"ref23","article-title":"M6-T: Exploring sparse expert models and beyond","author":"Yang","year":"2021","journal-title":"arXiv:2105.15082"},{"key":"ref24","article-title":"GShard: Scaling giant models with conditional computation and automatic sharding","author":"Lepikhin","year":"2020","journal-title":"arXiv:2006.16668"},{"key":"ref25","first-page":"17555","article-title":"Hash layers for large sparse models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Roller"},{"key":"ref26","article-title":"Augmenting self-attention with persistent memory","author":"Sukhbaatar","year":"2019","journal-title":"arXiv:1907.01470"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.findings-emnlp.432"},{"key":"ref28","article-title":"WormKAN: Are KAN effective for identifying and tracking concept drift in time series?","author":"Xu","year":"2024","journal-title":"arXiv:2410.10041"},{"key":"ref29","article-title":"Kolmogorov\u2013Arnold networks for time series: Bridging predictive power and interpretability","author":"Xu","year":"2024","journal-title":"arXiv:2406.02496"},{"key":"ref30","article-title":"Exploring Kolmogorov\u2013Arnold networks for realistic image sharpness assessment","author":"Yu","year":"2024","journal-title":"arXiv:2409.07762"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i5.32491"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.3390\/e27060593"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CANDARW64572.2024.00026"},{"key":"ref34","article-title":"A temporal Kolmogorov\u2013Arnold transformer for time series forecasting","author":"Genet","year":"2024","journal-title":"arXiv:2406.02486"},{"key":"ref35","article-title":"GKAN: Graph Kolmogorov\u2013Arnold networks","author":"Kiamari","year":"2024","journal-title":"arXiv:2406.06470"},{"key":"ref36","article-title":"Kolmogorov\u2013Arnold networks in low-data regimes: A comparative study with multilayer perceptrons","author":"Pourkamali-Anaraki","year":"2024","journal-title":"arXiv:2409.10463"},{"key":"ref37","article-title":"Convolutional Kolmogorov\u2013Arnold networks","author":"Dylan Bodner","year":"2024","journal-title":"arXiv:2406.13155"},{"key":"ref38","article-title":"Smooth Kolmogorov Arnold networks enabling structural knowledge representation","author":"Samadi","year":"2024","journal-title":"arXiv:2405.11318"},{"key":"ref39","article-title":"Endowing interpretability for neural cognitive diagnosis by efficient Kolmogorov\u2013Arnold networks","author":"Yang","year":"2024","journal-title":"arXiv:2405.14399"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/JBHI.2024.3471928"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/tvt.2025.3553860"},{"key":"ref42","article-title":"Kolmogorov\u2013Arnold transformer","author":"Yang","year":"2024","journal-title":"arXiv:2409.10594"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.3390\/app142210173"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1140\/epjqt\/s40507-024-00289-z"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.7717\/peerj-cs.1224"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.3390\/math11041006"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W15-3049"},{"key":"ref49","first-page":"65","article-title":"METEOR: An automatic metric for MT evaluation with improved correlation with human judgments","volume-title":"Proc. ACL Workshop Intrinsic Extrinsic Eval. Measures Mach. Transl. Summarization","author":"Banerjee"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/10820123\/11131148.pdf?arnumber=11131148","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,28]],"date-time":"2025-08-28T04:33:52Z","timestamp":1756355632000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11131148\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":49,"URL":"https:\/\/doi.org\/10.1109\/access.2025.3601069","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}