{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,1]],"date-time":"2025-11-01T17:32:52Z","timestamp":1762018372025,"version":"3.40.3"},"publisher-location":"Cham","reference-count":22,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030765071"},{"type":"electronic","value":"9783030765088"}],"license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021]]},"DOI":"10.1007\/978-3-030-76508-8_11","type":"book-chapter","created":{"date-parts":[[2021,5,15]],"date-time":"2021-05-15T07:02:58Z","timestamp":1621062178000},"page":"130-139","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["How BERT\u2019s Dropout Fine-Tuning Affects Text Classification?"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2874-6862","authenticated-orcid":false,"given":"Salma","family":"El Anigri","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0166-0177","authenticated-orcid":false,"given":"Mohammed Majid","family":"Himmi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4141-0623","authenticated-orcid":false,"given":"Abdelhak","family":"Mahmoudi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2021,5,16]]},"reference":[{"key":"11_CR1","unstructured":"Adhikari, A., Ram, A., Tang, R., Lin, J.: DocBERT: BERT for document classification. arXiv preprint arXiv:190408398 (2019)"},{"key":"11_CR2","doi-asserted-by":"publisher","first-page":"135","DOI":"10.1162\/tacl_a_00051","volume":"5","author":"P Bojanowski","year":"2017","unstructured":"Bojanowski, P., Grave, E., Joulin, A., Mikolov, T.: Enriching word vectors with subword information. Trans. Assoc. Comput. Linguist. 5, 135\u2013146 (2017)","journal-title":"Trans. Assoc. Comput. Linguist."},{"key":"11_CR3","unstructured":"Dai, A.M., Le, Q.V.: Semi-supervised sequence learning. In: Cortes, C., Lawrence, N., Lee, D., Sugiyama, M., Garnett, R. (eds.) Advances in Neural Information Processing Systems, vol. 28. Curran Associates Inc. (2015). https:\/\/proceedings.neurips.cc\/paper\/2015\/file\/7137debd45ae4d0ab9aa953017286b20-Paper.pdf"},{"key":"11_CR4","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:181004805 (2018)"},{"key":"11_CR5","unstructured":"Dodge, J., Ilharco, G., Schwartz, R., Farhadi, A., Hajishirzi, H., Smith, N.: Fine-tuning pretrained language models: weight initializations, data orders, and early stopping. arXiv preprint arXiv:200206305 (2020)"},{"key":"11_CR6","doi-asserted-by":"publisher","unstructured":"Howard, J., Ruder, S.: Universal language model fine-tuning for text classification. In: Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 328\u2013339. Association for Computational Linguistics, Melbourne (2018). https:\/\/doi.org\/10.18653\/v1\/P18-1031. https:\/\/www.aclweb.org\/anthology\/P18-1031","DOI":"10.18653\/v1\/P18-1031"},{"key":"11_CR7","doi-asserted-by":"publisher","unstructured":"Huang, L., Ma, D., Li, S., Zhang, X., Wang, H.: Text level graph neural network for text classification. In: Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), pp. 3444\u20133450. Association for Computational Linguistics, Hong Kong (2019). https:\/\/doi.org\/10.18653\/v1\/D19-1345. https:\/\/www.aclweb.org\/anthology\/D19-1345","DOI":"10.18653\/v1\/D19-1345"},{"key":"11_CR8","doi-asserted-by":"publisher","unstructured":"Kim, Y.: Convolutional neural networks for sentence classification. In: Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP), pp. 1746\u20131751. Association for Computational Linguistics, Doha (2014). https:\/\/doi.org\/10.3115\/v1\/D14-1181. https:\/\/www.aclweb.org\/anthology\/D14-1181","DOI":"10.3115\/v1\/D14-1181"},{"key":"11_CR9","unstructured":"Lan, Z., Chen, M., Goodman, S., Gimpel, K., Sharma, P., Soricut, R.: ALBERT: a lite BERT for self-supervised learning of language representations. arXiv preprint arXiv:190911942 (2019)"},{"key":"11_CR10","unstructured":"Lee, C., Cho, K., Kang, W.: Mixout: effective regularization to finetune large-scale pretrained language models. In: International Conference on Learning Representations (2020). https:\/\/openreview.net\/forum?id=HkgaETNtDB"},{"key":"11_CR11","unstructured":"Liu, Y., et al.: RoBERTa: a robustly optimized BERT pretraining approach. arXiv preprint arXiv:190711692 (2019)"},{"key":"11_CR12","unstructured":"Loshchilov, I., Hutter, F.: Decoupled weight decay regularization. In: International Conference on Learning Representations (2019). https:\/\/openreview.net\/forum?id=Bkg6RiCqY7"},{"key":"11_CR13","unstructured":"Mikolov, T., Chen, K., Corrado, G., Dean, J.: Efficient estimation of word representations in vector space. arXiv preprint arXiv:13013781 (2013)"},{"key":"11_CR14","doi-asserted-by":"crossref","unstructured":"Pennington, J., Socher, R., Manning, C.D.: GloVe: global vectors for word representation. In: Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP), pp. 1532\u20131543 (2014)","DOI":"10.3115\/v1\/D14-1162"},{"key":"11_CR15","unstructured":"Peters, M.E., et al.: Deep contextualized word representations. arXiv preprint arXiv:180205365 (2018)"},{"key":"11_CR16","unstructured":"Radford, A., Narasimhan, K., Salimans, T., Sutskever, I.: Improving language understanding with unsupervised learning (2018)"},{"key":"11_CR17","doi-asserted-by":"publisher","unstructured":"Rajpurkar, P., Zhang, J., Lopyrev, K., Liang, P.: SQuAD: 100,000+ questions for machine comprehension of text. In: Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing, pp. 2383\u20132392. Association for Computational Linguistics, Austin (2016). https:\/\/doi.org\/10.18653\/v1\/D16-1264. https:\/\/www.aclweb.org\/anthology\/D16-1264","DOI":"10.18653\/v1\/D16-1264"},{"key":"11_CR18","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"194","DOI":"10.1007\/978-3-030-32381-3_16","volume-title":"Chinese Computational Linguistics","author":"C Sun","year":"2019","unstructured":"Sun, C., Qiu, X., Xu, Y., Huang, X.: How to fine-tune BERT for text classification? In: Sun, M., Huang, X., Ji, H., Liu, Z., Liu, Y. (eds.) CCL 2019. LNCS (LNAI), vol. 11856, pp. 194\u2013206. Springer, Cham (2019). https:\/\/doi.org\/10.1007\/978-3-030-32381-3_16"},{"key":"11_CR19","unstructured":"Vaswani, A., et al.: Attention is all you need. arXiv preprint arXiv:170603762 (2017)"},{"key":"11_CR20","unstructured":"Yang, Z., Dai, Z., Yang, Y., Carbonell, J., Salakhutdinov, R.R., Le, Q.V.: Xlnet: generalized autoregressive pretraining for language understanding. In: Wallach, H., Larochelle, H., Beygelzimer, A., d\u2019Alch\u00e9-Buc, F., Fox, E., Garnett, R. (eds.) Advances in Neural Information Processing Systems, vol. 32. Curran Associates Inc. (2019). https:\/\/proceedings.neurips.cc\/paper\/2019\/file\/dc6a7e655d7e5840e66733e9ee67cc69-Paper.pdf"},{"key":"11_CR21","doi-asserted-by":"publisher","unstructured":"Zellers, R., Bisk, Y., Schwartz, R., Choi, Y.: SWAG: a large-scale adversarial dataset for grounded commonsense inference. In: Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pp. 93\u2013104. Association for Computational Linguistics, Brussels (2018). https:\/\/doi.org\/10.18653\/v1\/D18-1009. https:\/\/www.aclweb.org\/anthology\/D18-1009","DOI":"10.18653\/v1\/D18-1009"},{"key":"11_CR22","unstructured":"Zhang, X., Zhao, J., LeCun, Y.: Character-level convolutional networks for text classification. arXiv preprint arXiv:150901626 (2015)"}],"container-title":["Lecture Notes in Business Information Processing","Business Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-76508-8_11","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,7]],"date-time":"2024-03-07T15:23:47Z","timestamp":1709825027000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-76508-8_11"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"ISBN":["9783030765071","9783030765088"],"references-count":22,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-76508-8_11","relation":{},"ISSN":["1865-1348","1865-1356"],"issn-type":[{"type":"print","value":"1865-1348"},{"type":"electronic","value":"1865-1356"}],"subject":[],"published":{"date-parts":[[2021]]},"assertion":[{"value":"16 May 2021","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"CBI","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Business Intelligence","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Beni-Mellal","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Morocco","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2021","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27 May 2021","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 May 2021","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"6","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"cbi2021","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.cbi-bm.com\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"EasyChair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"60","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"26","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"6","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"43% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"2","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}