{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,9]],"date-time":"2026-02-09T18:51:02Z","timestamp":1770663062014,"version":"3.49.0"},"publisher-location":"Cham","reference-count":33,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030613761","type":"print"},{"value":"9783030613778","type":"electronic"}],"license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2020]]},"DOI":"10.1007\/978-3-030-61377-8_38","type":"book-chapter","created":{"date-parts":[[2020,10,15]],"date-time":"2020-10-15T19:04:06Z","timestamp":1602788646000},"page":"551-565","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":11,"title":["Pre-trained Data Augmentation for Text Classification"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5208-0290","authenticated-orcid":false,"given":"Hugo","family":"Queiroz Abonizio","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4988-0702","authenticated-orcid":false,"given":"Sylvio","family":"Barbon Junior","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2020,10,13]]},"reference":[{"key":"38_CR1","unstructured":"Anaby-Tavor, A., et al.: Not enough data deep learning to the rescue. arXiv preprint arXiv:1911.03118 (2019)"},{"issue":"2","key":"38_CR2","first-page":"1137","volume":"3","author":"Y Bengio","year":"2003","unstructured":"Bengio, Y., Ducharme, R., Vincent, P., Jauvin, C.: A neural probabilistic language model. J. Mach. Learn. Res. 3(2), 1137\u20131155 (2003)","journal-title":"J. Mach. Learn. Res."},{"key":"38_CR3","unstructured":"Cubuk, E.D., Zoph, B., Mane, D., Vasudevan, V., Le, Q.V.: Autoaugment: learning augmentation policies from data (2019).https:\/\/arxiv.org\/pdf\/1805.09501.pdf"},{"key":"38_CR4","first-page":"1","volume":"7","author":"J Dem\u0161ar","year":"2006","unstructured":"Dem\u0161ar, J.: Statistical comparisons of classifiers over multiple data sets. J. Mach. Learn. Res. 7, 1\u201330 (2006)","journal-title":"J. Mach. Learn. Res."},{"key":"38_CR5","doi-asserted-by":"publisher","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. In: Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Vol. 1 (Long and Short Papers), pp. 4171\u20134186. Association for Computational Linguistics, Minneapolis, Minnesota, June 2019. https:\/\/doi.org\/10.18653\/v1\/N19-1423, https:\/\/www.aclweb.org\/anthology\/N19-1423","DOI":"10.18653\/v1\/N19-1423"},{"key":"38_CR6","doi-asserted-by":"publisher","unstructured":"Edunov, S., Ott, M., Auli, M., Grangier, D.: Understanding back-translation at scale. In: Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pp. 489\u2013500. Association for Computational Linguistics, Brussels, Belgium, Oct-Nov 2018. https:\/\/doi.org\/10.18653\/v1\/D18-1045, https:\/\/www.aclweb.org\/anthology\/D18-1045","DOI":"10.18653\/v1\/D18-1045"},{"key":"38_CR7","doi-asserted-by":"publisher","unstructured":"Fan, A., Lewis, M., Dauphin, Y.: Hierarchical neural story generation. In: Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 889\u2013898. Association for Computational Linguistics, Melbourne, Australia, July 2018. https:\/\/doi.org\/10.18653\/v1\/P18-1082, https:\/\/www.aclweb.org\/anthology\/P18-1082","DOI":"10.18653\/v1\/P18-1082"},{"key":"38_CR8","unstructured":"Gokaslan, A., Cohen, V.: Openwebtext corpus (2019). http:\/\/Skylion007.github.io\/OpenWebTextCorpus"},{"key":"38_CR9","unstructured":"Hinton, G., Vinyals, O., Dean, J.: Distilling the knowledge in a neural network. In: NIPS Deep Learning and Representation Learning Workshop (2015). http:\/\/arxiv.org\/abs\/1503.02531"},{"issue":"8","key":"38_CR10","doi-asserted-by":"publisher","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","volume":"9","author":"S Hochreiter","year":"1997","unstructured":"Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9(8), 1735\u20131780 (1997). https:\/\/doi.org\/10.1162\/neco.1997.9.8.1735","journal-title":"Neural Comput."},{"key":"38_CR11","unstructured":"Holtzman, A., Buys, J., Du, L., Forbes, M., Choi, Y.: The curious case of neural text degeneration. arXiv preprint arXiv:1904.09751 (2019)"},{"key":"38_CR12","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, Australia, July 2018. https:\/\/doi.org\/10.18653\/v1\/P18-1031, https:\/\/www.aclweb.org\/anthology\/P18-1031","DOI":"10.18653\/v1\/P18-1031"},{"key":"38_CR13","unstructured":"Hu, Z., Tan, B., Salakhutdinov, R.R., Mitchell, T.M., Xing, E.P.: Learning data manipulation for augmentation and weighting. In: Wallach, H., Larochelle, H., Beygelzimer, A., d\u00c1lch\u00e9-Buc, F., Fox, E., Garnett, R. (eds.) Advances in Neural Information Processing Systems, vol. 32, pp. 15764\u201315775. Curran Associates, Inc. (2019). http:\/\/papers.nips.cc\/paper\/9706-learning-data-manipulation-for-augmentation-and-weighting.pdf"},{"key":"38_CR14","doi-asserted-by":"publisher","first-page":"72","DOI":"10.1016\/j.ins.2015.10.039","volume":"332","author":"RA Igawa","year":"2016","unstructured":"Igawa, R.A., et al.: Account classification in online social networks with lbca and wavelets. Inform. Sci. 332, 72\u201383 (2016)","journal-title":"Inform. Sci."},{"key":"38_CR15","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, Qatar, October 2014. https:\/\/doi.org\/10.3115\/v1\/D14-1181, https:\/\/www.aclweb.org\/anthology\/D14-1181","DOI":"10.3115\/v1\/D14-1181"},{"key":"38_CR16","doi-asserted-by":"publisher","unstructured":"Kobayashi, S.: Contextual augmentation: data augmentation by words with paradigmatic relations. In: Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Vol. 2 (Short Papers), pp. 452\u2013457. Association for Computational Linguistics, New Orleans, Louisiana, June 2018. https:\/\/doi.org\/10.18653\/v1\/N18-2072, https:\/\/www.aclweb.org\/anthology\/N18-2072","DOI":"10.18653\/v1\/N18-2072"},{"key":"38_CR17","unstructured":"Kolomiyets, O., Bethard, S., Moens, M.F.: Model-portability experiments for textual temporal analysis. In: Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies: Short Papers, Vol. 2, pp. 271\u2013276. HLT \u201911, Association for Computational Linguistics, USA (2011)"},{"key":"38_CR18","unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. In: Advances in Neural Information Processing Systems, pp. 1097\u20131105 (2012)"},{"key":"38_CR19","unstructured":"Kumar, V., Choudhary, A., Cho, E.: Data augmentation using pre-trained transformer models. arXiv preprint arXiv:2003.02245 (2020)"},{"key":"38_CR20","doi-asserted-by":"publisher","unstructured":"Petroni, F., et al.: Language models as knowledge bases. 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. 2463\u20132473. Association for Computational Linguistics, Hong Kong, China, November 2019. https:\/\/doi.org\/10.18653\/v1\/D19-1250, https:\/\/www.aclweb.org\/anthology\/D19-1250","DOI":"10.18653\/v1\/D19-1250"},{"key":"38_CR21","unstructured":"Sanh, V., Debut, L., Chaumond, J., Wolf, T.: Distilbert, a distilled version of bert: smaller, faster, cheaper and lighter. arXiv preprint arXiv:1910.01108 (2019)"},{"key":"38_CR22","unstructured":"Schwartz, R., Dodge, J., Smith, N.A., Etzioni, O.: Green ai. ArXiv abs\/1907.10597 (2019)"},{"key":"38_CR23","doi-asserted-by":"publisher","unstructured":"Sennrich, R., Haddow, B., Birch, A.: Improving neural machine translation models with monolingual data. In: Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 86\u201396. Association for Computational Linguistics, Berlin, Germany, Auguest 2016. https:\/\/doi.org\/10.18653\/v1\/P16-1009, https:\/\/www.aclweb.org\/anthology\/P16-1009","DOI":"10.18653\/v1\/P16-1009"},{"key":"38_CR24","unstructured":"Shleifer, S.: Low resource text classification with ulmfit and backtranslation. arXiv preprint arXiv:1903.09244 (2019)"},{"key":"38_CR25","unstructured":"Socher, R., et al.: Recursive deep models for semantic compositionality over a sentiment treebank. In: Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing, pp. 1631\u20131642 (2013)"},{"key":"38_CR26","doi-asserted-by":"publisher","unstructured":"Strubell, E., Ganesh, A., McCallum, A.: Energy and policy considerations for deep learning in NLP. In: Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pp. 3645\u20133650. Association for Computational Linguistics, Florence, Italy, July 2019. https:\/\/doi.org\/10.18653\/v1\/P19-1355, https:\/\/www.aclweb.org\/anthology\/P19-1355","DOI":"10.18653\/v1\/P19-1355"},{"key":"38_CR27","unstructured":"Wang, S., Manning, C.D.: Baselines and bigrams: simple, good sentiment and topic classification. In: Proceedings of the 50th Annual Meeting of the Association for Computational Linguistics: Short Papers, vol. 2, pp. 90\u201394. Association for Computational Linguistics (2012)"},{"key":"38_CR28","doi-asserted-by":"publisher","unstructured":"Wei, J., Zou, K.: EDA: easy data augmentation techniques for boosting performance on text classification tasks. In: Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing (EMNLP-IJCNLP), pp. 6382\u20136388. Association for Computational Linguistics, Hong Kong, China, November 2019. https:\/\/doi.org\/10.18653\/v1\/D19-1670, https:\/\/www.aclweb.org\/anthology\/D19-1670","DOI":"10.18653\/v1\/D19-1670"},{"key":"38_CR29","unstructured":"Wolf, T., et al.: Huggingface\u2019s transformers: state-of-the-art natural language processing. ArXiv abs\/1910.03771 (2019)"},{"key":"38_CR30","doi-asserted-by":"crossref","unstructured":"Wong, S.C., Gatt, A., Stamatescu, V., McDonnell, M.D.: Understanding data augmentation for classification: when to warp. In: 2016 International Conference on Digital Image Computing: Techniques and Applications (DICTA), pp. 1\u20136. IEEE (2016)","DOI":"10.1109\/DICTA.2016.7797091"},{"key":"38_CR31","unstructured":"Yogatama, D., Dyer, C., Ling, W., Blunsom, P.: Generative and discriminative text classification with recurrent neural networks. arXiv preprint arXiv:1703.01898 (2017)"},{"key":"38_CR32","unstructured":"Yu, A.W., Dohan, D., Luong, T., Zhao, R., Chen, K., Le, Q.: Qanet: combining local convolution with global self-attention for reading comprehension (2018). https:\/\/openreview.net\/pdf?id=B14TlG-RW"},{"key":"38_CR33","unstructured":"Zhang, X., Zhao, J., LeCun, Y.: Character-level convolutional networks for text classification. In: Proceedings of the 28th International Conference on Neural Information Processing Systems, Vol. 1, pp. 649\u2013657. NIPS\u201915, MIT Press, Cambridge, MA, USA (2015)"}],"container-title":["Lecture Notes in Computer Science","Intelligent Systems"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-61377-8_38","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,11,12]],"date-time":"2020-11-12T09:58:57Z","timestamp":1605175137000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-030-61377-8_38"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"ISBN":["9783030613761","9783030613778"],"references-count":33,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-61377-8_38","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020]]},"assertion":[{"value":"13 October 2020","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"BRACIS","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Brazilian Conference on Intelligent Systems","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Rio Grande","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Brazil","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2020","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"20 October 2020","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 October 2020","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"9","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"bracis2020","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www2.sbc.org.br\/bracis2020\/","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":"JEMS","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"228","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":"91","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":"0","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":"40% - 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":"3,5","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":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Due to the Corona pandemic BRACIS 2020 was held as a virtual event.","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}