{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,5]],"date-time":"2026-06-05T16:13:05Z","timestamp":1780675985429,"version":"3.54.1"},"reference-count":64,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"Researchers Supporting Project number","award":["RSPD2024R1051"],"award-info":[{"award-number":["RSPD2024R1051"]}]},{"name":"King Saud University, Riyadh, Saudi Arabia"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/access.2024.3465631","type":"journal-article","created":{"date-parts":[[2024,9,23]],"date-time":"2024-09-23T17:29:20Z","timestamp":1727112560000},"page":"139113-139128","source":"Crossref","is-referenced-by-count":36,"title":["Advances in Pruning and Quantization for Natural Language Processing"],"prefix":"10.1109","volume":"12","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-3308-7670","authenticated-orcid":false,"given":"Ummara","family":"Bibi","sequence":"first","affiliation":[{"name":"Department of Electrical and Computer Engineering, COMSATS University Islamabad, Islamabad, Pakistan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-5045-4871","authenticated-orcid":false,"given":"Mahrukh","family":"Mazhar","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, COMSATS University Islamabad, Islamabad, Pakistan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5322-9808","authenticated-orcid":false,"given":"Dilshad","family":"Sabir","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, COMSATS University Islamabad, Islamabad, Pakistan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6970-2612","authenticated-orcid":false,"given":"Muhammad","family":"Fasih Uddin Butt","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, COMSATS University Islamabad, Islamabad, Pakistan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1505-5157","authenticated-orcid":false,"given":"Ali","family":"Hassan","sequence":"additional","affiliation":[{"name":"Department of Computer and Software Engineering, College of Electrical and Mechanical Engineering, National University of Sciences and Technology, Islamabad, Pakistan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1967-6273","authenticated-orcid":false,"given":"Mustansar","family":"Ali Ghazanfar","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Digital Technologies, School of Architecture, Computing and Engineering, University of East London, London, U.K."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6062-0098","authenticated-orcid":false,"given":"Arshad","family":"Ali Khan","sequence":"additional","affiliation":[{"name":"5Here East, Queen Elizabeth Olympic Park, Plexal, London, U.K."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6871-6633","authenticated-orcid":false,"given":"Wadood","family":"Abdul","sequence":"additional","affiliation":[{"name":"Department of Computer Engineering, College of Computer and Information Sciences, King Saud University, Riyadh, Saudi Arabia"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"The natural language decathlon: Multitask learning as question answering","author":"McCann","year":"2018","journal-title":"arXiv:1806.08730"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.47672\/ejt.1473"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-022-13428-4"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00411"},{"key":"ref5","first-page":"10323","article-title":"SparseGPT: Massive language models can be accurately pruned in one-shot","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Frantar"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2019.105210"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICISCAE.2018.8666928"},{"key":"ref8","article-title":"Comparative study of CNN and RNN for natural language processing","author":"Yin","year":"2017","journal-title":"arXiv:1702.01923"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-023-14450-w"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2023.3293716"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.2478\/s13537-013-0109-x"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2022.101429"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-acl.300"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-87481-2_3"},{"key":"ref15","article-title":"Generalization bounds for magnitude-based pruning via sparse matrix sketching","author":"Guha","year":"2023","journal-title":"arXiv:2305.18789"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3576842.3589175"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-19-9228-5_53"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01544"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095780"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2022.105535"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2023.02.004"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01384"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP46576.2022.9898051"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO50266.2020.00071"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3069906"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.3390\/electronics10030351"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1155\/2021\/9208138"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/BigData47090.2019.9006030"},{"key":"ref29","article-title":"Compressing word embeddings via deep compositional code learning","author":"Shu","year":"2017","journal-title":"arXiv:1711.01068"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2021.07.045"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02170"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA51647.2021.00018"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.21437\/Eurospeech.2001-8"},{"key":"ref34","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018","journal-title":"arXiv:1810.04805"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.repl4nlp-1.18"},{"key":"ref36","article-title":"Accelerating sparse deep neural networks","author":"Mishra","year":"2021","journal-title":"arXiv:2104.08378"},{"key":"ref37","first-page":"348","article-title":"Accurate and efficient 2-bit quantized neural networks","volume-title":"Proc. Mach. Learn. Syst.","volume":"1","author":"Choi"},{"key":"ref38","article-title":"PACT: Parameterized clipping activation for quantized neural networks","author":"Choi","year":"2018","journal-title":"arXiv:1805.06085"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA52012.2021.00021"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1145\/3079856.3080246"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1264"},{"key":"ref42","article-title":"HuggingFace\u2019s transformers: State-of-the-art natural language processing","author":"Wolf","year":"2019","journal-title":"arXiv:1910.03771"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-acl.363"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1907.11692"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1145\/3007787.3001138"},{"key":"ref46","first-page":"1631","article-title":"Recursive deep models for semantic compositionality over a sentiment treebank","volume-title":"Proc. Conf. Empir. Methods Nat. Lang. Process.","author":"Socher"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.findings-emnlp.1"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICFPT47387.2019.00045"},{"key":"ref49","first-page":"1","article-title":"Groupreduce: Block-wise low-rank approximation for neural language model shrinking","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"31","author":"Chen"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01249-6_45"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00821"},{"key":"ref52","article-title":"Convolutional neural network compression for natural language processing","author":"Wr\u00f3bel","year":"2018","journal-title":"arXiv:1805.10796"},{"key":"ref53","article-title":"A sensitivity analysis of (and practitioners\u2019 guide to) convolutional neural networks for sentence classification","author":"Zhang","year":"2015","journal-title":"arXiv:1510.03820"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2021\/472"},{"key":"ref56","article-title":"SNAS: Stochastic neural architecture search","author":"Xie","year":"2018","journal-title":"arXiv:1812.09926"},{"key":"ref57","article-title":"Estimating or propagating gradients through stochastic neurons for conditional computation","author":"Bengio","year":"2013","journal-title":"arXiv:1308.3432"},{"key":"ref58","article-title":"Towards optimal compression: Joint pruning and quantization","author":"Zandonati","year":"2023","journal-title":"arXiv:2302.07612"},{"key":"ref59","article-title":"Combining compressions for multiplicative size scaling on natural language tasks","author":"Movva","year":"2022","journal-title":"arXiv:2208.09684"},{"key":"ref60","first-page":"14140","article-title":"Deep compression of pre-trained transformer models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Wang"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.240"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1145\/3467476"},{"key":"ref63","article-title":"Measure and improve robustness in NLP models: A survey","author":"Wang","year":"2021","journal-title":"arXiv:2112.08313"},{"key":"ref64","first-page":"5741","article-title":"Bayesian bits: Unifying quantization and pruning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Van Baalen"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/10380310\/10685352.pdf?arnumber=10685352","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,10]],"date-time":"2024-10-10T11:34:16Z","timestamp":1728560056000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10685352\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":64,"URL":"https:\/\/doi.org\/10.1109\/access.2024.3465631","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}