{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,20]],"date-time":"2026-04-20T10:29:53Z","timestamp":1776680993912,"version":"3.51.2"},"reference-count":61,"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\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2023]]},"DOI":"10.1109\/access.2023.3336311","type":"journal-article","created":{"date-parts":[[2023,11,23]],"date-time":"2023-11-23T19:09:06Z","timestamp":1700766546000},"page":"132516-132531","source":"Crossref","is-referenced-by-count":24,"title":["Data Augmentation Using Transformers and Similarity Measures for Improving Arabic Text Classification"],"prefix":"10.1109","volume":"11","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4599-8797","authenticated-orcid":false,"given":"Dania","family":"Refai","sequence":"first","affiliation":[{"name":"Computer Science Department, Princess Sumaya University for Technology, Amman, Jordan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9144-9409","authenticated-orcid":false,"given":"Saleh","family":"Abu-Soud","sequence":"additional","affiliation":[{"name":"Data Science Department, Princess Sumaya University for Technology, Amman, Jordan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5788-6656","authenticated-orcid":false,"given":"Mohammad J.","family":"Abdel-Rahman","sequence":"additional","affiliation":[{"name":"Data Science Department, Princess Sumaya University for Technology, Amman, Jordan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.5120\/ijca2016907355"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-14596-5"},{"key":"ref3","first-page":"5","article-title":"Deep learning for NLP (without magic)","volume-title":"Proc. 50th Annu. Meeting Assoc. Comput. Linguistics (ACL), Tutorial Abstr.","author":"Socher"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1670"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.semeval-1.246"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.coling-main.343"},{"key":"ref7","article-title":"BET: A backtranslation approach for easy data augmentation in transformer-based paraphrase identification context","author":"Corbeil","year":"2020","journal-title":"arXiv:2009.12452"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1186\/s40537-019-0197-0"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-acl.84"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/j.aiopen.2022.10.001"},{"key":"ref12","first-page":"1234","article-title":"Sequence-to-sequence data augmentation for dialogue language understanding","volume-title":"Proc. 27th Int. Conf. Comput. Linguistics","author":"Hou"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i14.17540"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.631"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.eacl-main.89"},{"key":"ref16","article-title":"Evaluation of text generation: A survey","author":"Celikyilmaz","year":"2020","journal-title":"arXiv:2006.14799"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1016\/0146-664X(80)90054-4"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/281250.281256"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/BF02365362"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.naacl-main.57"},{"key":"ref22","article-title":"Can we achieve more with less? Exploring data augmentation for toxic comment classification","author":"Rastogi","year":"2020","journal-title":"arXiv:2007.00875"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-36204-1_19"},{"key":"ref24","first-page":"6256","article-title":"Unsupervised data augmentation for consistency training","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Xie"},{"issue":"2","key":"ref25","first-page":"28","article-title":"Arabic language: historic and sociolinguistic characteristics","volume":"1","author":"Al-Huri","year":"2015","journal-title":"English Literature Lang. Rev."},{"key":"ref26","volume-title":"Summary by Language Size","year":"2020"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.11591\/ijece.v10i6.pp6629-6643"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.7717\/peerj-cs.469"},{"key":"ref29","article-title":"Accenture at CheckThat! 2021: Interesting claim identification and ranking with contextually sensitive lexical training data augmentation","author":"Williams","year":"2021","journal-title":"arXiv:2107.05684"},{"key":"ref30","first-page":"370","article-title":"The IDC system for sentiment classification and sarcasm detection in Arabic","volume-title":"Proc. Arabic Natural Lang. Process. Workshop","author":"Israeli"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1016\/j.procs.2021.05.092"},{"key":"ref32","first-page":"196","article-title":"AraGPT2: Pre-trained transformer for Arabic language generation","volume-title":"Proc. Arabic Natural Lang. Process. Workshop","author":"Antoun"},{"key":"ref33","first-page":"9","article-title":"AraBERT: Transformer-based model for Arabic language understanding","volume-title":"Proc. LREC Workshop Lang. Resour. Eval. Conf.","author":"Anton"},{"key":"ref34","first-page":"275","article-title":"Arabic dialect identification: An Arabic-BERT model with data augmentation and ensembling strategy","volume-title":"Proc. Arabic Natural Lang. Process. Workshop","author":"Gaanoun"},{"key":"ref35","first-page":"207","article-title":"BERT transformer model for detecting Arabic GPT2 auto-generated tweets","volume-title":"Proc. Arabic Natural Lang. Process. Workshop","author":"Harrag"},{"key":"ref36","first-page":"312","article-title":"Sarcasm and sentiment detection in Arabic tweets using BERT-based models and data augmentation","volume-title":"Proc. Arabic Natural Lang. Process. Workshop","author":"Abuzayed"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICICS55353.2022.9811153"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/JEEIT53412.2021.9634095"},{"key":"ref39","first-page":"191","article-title":"AraELECTRA: Pre-training text discriminators for Arabic language understanding","volume-title":"Proc. Arabic Natural Lang. Process. Workshop","author":"Antoun"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1016\/j.procs.2021.05.072"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.3390\/info10040150"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.24996\/ijs.2022.63.1.37"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1504\/ijcat.2019.10020108"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/n16-3003"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1155\/2021\/5516945"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.551"},{"key":"ref47","article-title":"An empirical survey of data augmentation for limited data learning in NLP","author":"Chen","year":"2021","journal-title":"arXiv:2106.07499"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1016\/j.aiopen.2022.03.001"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.wanlp-1.11"},{"key":"ref50","article-title":"Context-gloss augmentation for improving Arabic target sense verification","author":"Malaysha","year":"2023","journal-title":"arXiv:2302.03126"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-18117-2_2"},{"key":"ref52","article-title":"Word embeddings: A survey","author":"Almeida","year":"2019","journal-title":"arXiv:1901.09069"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-28940-3_10"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1410"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1002\/widm.1253"},{"key":"ref56","first-page":"441","article-title":"The \u2018k\u2019 in k-fold cross validation","volume-title":"Proc. Eur. Symp. Artif. Neural Netw., Comput. Intell. Mach. Learn. (ESANN)","author":"Anguita"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D15-1299"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.coling-main.611"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CCNS50731.2020.00049"},{"key":"ref60","volume-title":"Arabic-Data-Augmentation","author":"Refai","year":"2023"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1007\/978-94-6351-086-8_4"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/10005208\/10328600.pdf?arnumber=10328600","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,3]],"date-time":"2024-03-03T03:53:24Z","timestamp":1709438004000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10328600\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":61,"URL":"https:\/\/doi.org\/10.1109\/access.2023.3336311","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]}}}