{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,2]],"date-time":"2026-05-02T07:02:49Z","timestamp":1777705369011,"version":"3.51.4"},"reference-count":4,"publisher":"SAGE Publications","issue":"2","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IFS"],"published-print":{"date-parts":[[2023,1,30]]},"abstract":"<jats:p>MobileBert is a generic lightweight model suffering from a large network depth and parameter cardinality. Therefore, this paper proposes a secondary lightweight model entitled LightMobileBert, which retains the bottom 12 Transformers structure of the pre-trained MobileBert and utilizes the tensor decomposition technique to process the model to skip pre-training and further reduce the parameters. At the same time, the joint loss function is constructed based on the improved Supervised Contrastive Learning loss function and the Cross-Entropy loss function to improve performance and stability. Finally, the LMBert_Adam optimizer, an improved Bert_Adam optimizer, is used to optimize the model. The experimental results demonstrate that LightMobileBert has a comparatively higher performance than MobileBert and other popular models while requiring 57% fewer network parameters than MobileBert, confirming that LightMobileBert retains a higher performance while being lightweight.<\/jats:p>","DOI":"10.3233\/jifs-221985","type":"journal-article","created":{"date-parts":[[2022,10,25]],"date-time":"2022-10-25T11:21:54Z","timestamp":1666696914000},"page":"2117-2129","source":"Crossref","is-referenced-by-count":2,"title":["LightMobileBert: A secondary lightweight model based on MobileBert"],"prefix":"10.1177","volume":"44","author":[{"given":"Deguang","family":"Chen","sequence":"first","affiliation":[{"name":"School of Computer Science, Shaanxi Normal University, Xi\u2019an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jie","family":"Zhou","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence and Computer Science, Jiangnan University, Wuxi, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"179","reference":[{"key":"10.3233\/JIFS-221985_ref2","doi-asserted-by":"crossref","first-page":"5807","DOI":"10.3233\/JIFS-200581","article-title":"A text-based multi-span network for reading comprehension","volume":"41","author":"Chen","year":"2021","journal-title":"Journal of Intelligent & Fuzzy Systems"},{"key":"10.3233\/JIFS-221985_ref3","first-page":"1","article-title":"MTQA: Text-based multitype question and answer reading comprehension model","volume":"2021","author":"Chen","year":"2021","journal-title":"Computational Intelligence and Neuroscience"},{"key":"10.3233\/JIFS-221985_ref22","first-page":"18661","article-title":"Supervised contrastive learning","volume":"33","author":"Khosla","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.3233\/JIFS-221985_ref33","doi-asserted-by":"crossref","first-page":"625","DOI":"10.1162\/tacl_a_00290","article-title":"Neural network acceptability judgments","volume":"7","author":"Warstadt","year":"2019","journal-title":"Transactions of the Association for Computational Linguistics"}],"container-title":["Journal of Intelligent &amp; Fuzzy Systems"],"original-title":[],"link":[{"URL":"https:\/\/content.iospress.com\/download?id=10.3233\/JIFS-221985","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T09:43:39Z","timestamp":1777455819000},"score":1,"resource":{"primary":{"URL":"https:\/\/journals.sagepub.com\/doi\/full\/10.3233\/JIFS-221985"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,1,30]]},"references-count":4,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.3233\/jifs-221985","relation":{},"ISSN":["1064-1246","1875-8967"],"issn-type":[{"value":"1064-1246","type":"print"},{"value":"1875-8967","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,1,30]]}}}