{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,29]],"date-time":"2026-07-29T05:44:08Z","timestamp":1785303848528,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":47,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,7,18]],"date-time":"2023-07-18T00:00:00Z","timestamp":1689638400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"FAPEMIG"},{"name":"CAPES"},{"name":"FAPESP"},{"DOI":"10.13039\/100008536","name":"Amazon Web Services","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100008536","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100007065","name":"Nvidia","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100007065","id-type":"DOI","asserted-by":"publisher"}]},{"name":"CNPq"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,7,19]]},"DOI":"10.1145\/3539618.3591638","type":"proceedings-article","created":{"date-parts":[[2023,7,19]],"date-time":"2023-07-19T00:22:23Z","timestamp":1689726143000},"page":"665-674","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":32,"title":["An Effective, Efficient, and Scalable Confidence-based Instance Selection Framework for Transformer-Based Text Classification"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1988-8412","authenticated-orcid":false,"given":"Washington","family":"Cunha","sequence":"first","affiliation":[{"name":"Federal University of Minas Gerais, Belo Horizonte, Brazil"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0251-7172","authenticated-orcid":false,"given":"Celso","family":"Fran\u00e7a","sequence":"additional","affiliation":[{"name":"Federal University of Minas Gerais, Belo Horizonte, Brazil"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-7862-8701","authenticated-orcid":false,"given":"Guilherme","family":"Fonseca","sequence":"additional","affiliation":[{"name":"Federal University of S\u00e3o Jo\u00e3o del Rei, S\u00e3o Jo\u00e3o del Rei, Brazil"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4913-4902","authenticated-orcid":false,"given":"Leonardo","family":"Rocha","sequence":"additional","affiliation":[{"name":"Federal University of S\u00e3o Jo\u00e3o del Rei, S\u00e3o Jo\u00e3o del Rei, Brazil"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2075-3363","authenticated-orcid":false,"given":"Marcos Andr\u00e9","family":"Gon\u00e7alves","sequence":"additional","affiliation":[{"name":"Federal University of Minas Gerais, Belo Horizonte, Brazil"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2023,7,18]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Instance-based learning algorithms. Machine learning","author":"Aha David W","year":"1991","unstructured":"David W Aha, Dennis Kibler, and Marc K Albert. 1991. Instance-based learning algorithms. Machine learning, Vol. 6, 1 (1991), 37--66."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ipm.2020.102289"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"crossref","unstructured":"Glenn W Brier et al. 1950. Verification of forecasts expressed in terms of probability. Monthly weather review Vol. 78 1 (1950) 1--3.","DOI":"10.1175\/1520-0493(1950)078<0001:VOFEIT>2.0.CO;2"},{"key":"e_1_3_2_1_4_1","unstructured":"Tom Brown Benjamin Mann Nick Ryder Melanie Subbiah Jared D Kaplan Prafulla Dhariwal Arvind Neelakantan Pranav Shyam Girish Sastry Amanda Askell Sandhini Agarwal Ariel Herbert-Voss Gretchen Krueger Tom Henighan Rewon Child Aditya Ramesh Daniel Ziegler Jeffrey Wu Clemens Winter Chris Hesse Mark Chen Eric Sigler Mateusz Litwin Scott Gray Benjamin Chess Jack Clark Christopher Berner Sam McCandlish Alec Radford Ilya Sutskever and Dario Amodei. 2020. Language Models are Few-Shot Learners. In Advances in Neural Information Processing Systems."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W18-5406"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/3331184.3331239"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICTAI.2018.00053"},{"key":"e_1_3_2_1_8_1","volume-title":"Ranked batch-mode active learning. Info. Sciences","author":"Cardoso Thiago","year":"2017","unstructured":"Thiago Cardoso, Rodrigo Silva, S\u00e9rgio Canuto, Mirella Moro, and Marcos Goncc alves. 2017. Ranked batch-mode active learning. Info. Sciences (2017)."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3462919"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ipm.2020.102263"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ipm.2020.102481"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/3582000"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ipm.2023.103336"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2018.02.014"},{"key":"e_1_3_2_1_15_1","volume-title":"Proceedings of the Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (HLT-NAACL).","author":"Devlin Jacob","year":"2019","unstructured":"Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2019. BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. In Proceedings of the Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (HLT-NAACL)."},{"key":"e_1_3_2_1_16_1","volume-title":"Proceedings of the 39th International Conference on Machine Learning, Kamalika Chaudhuri, Stefanie Jegelka, Le Song, Csaba Szepesvari, Gang Niu, and Sivan Sabato (Eds.)","volume":"162","author":"Ethayarajh Kawin","year":"2022","unstructured":"Kawin Ethayarajh, Yejin Choi, and Swabha Swayamdipta. 2022. Understanding Dataset Difficulty with $mathcalV$-Usable Information. In Proceedings of the 39th International Conference on Machine Learning, Kamalika Chaudhuri, Stefanie Jegelka, Le Song, Csaba Szepesvari, Gang Niu, and Sivan Sabato (Eds.), Vol. 162. PMLR."},{"key":"e_1_3_2_1_17_1","volume-title":"Prototype selection for nearest neighbor classification: Taxonomy and empirical study","author":"Garcia Salvador","year":"2012","unstructured":"Salvador Garcia, Joaquin Derrac, Jose Cano, and Francisco Herrera. 2012. Prototype selection for nearest neighbor classification: Taxonomy and empirical study. IEEE transactions on pattern analysis and machine intelligence, Vol. 34, 3 (2012)."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/3459637.3482204"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/3471158.3472261"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.1968.1054155"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1093\/biomet\/75.4.800"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/160688.160758"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/E17-2068"},{"key":"e_1_3_2_1_24_1","volume-title":"Albert: A lite bert for self-supervised learning of language representations. arXiv preprint arXiv:1909.11942","author":"Lan Zhenzhong","year":"2019","unstructured":"Zhenzhong Lan, Mingda Chen, Sebastian Goodman, Kevin Gimpel, Piyush Sharma, and Radu Soricut. 2019. Albert: A lite bert for self-supervised learning of language representations. arXiv preprint arXiv:1909.11942 (2019)."},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.703"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2014.10.001"},{"key":"e_1_3_2_1_27_1","volume-title":"A Survey on Text Classification: From Traditional to Deep Learning. ACM Transactions on Intelligent Systems and Technology","author":"Li Qian","year":"2022","unstructured":"Qian Li, Hao Peng, Jianxin Li, Congying Xia, Renyu Yang, Lichao Sun, Philip S Yu, and Lifang He. 2022. A Survey on Text Classification: From Traditional to Deep Learning. ACM Transactions on Intelligent Systems and Technology (2022)."},{"key":"e_1_3_2_1_28_1","volume-title":"Roberta: A robustly optimized bert pretraining approach. arXiv preprint","author":"Liu Yinhan","year":"2019","unstructured":"Yinhan Liu, Myle Ott, Naman Goyal, Jingfei Du, Mandar Joshi, Danqi Chen, Omer Levy, Mike Lewis, Luke Zettlemoyer, and Veselin Stoyanov. 2019. Roberta: A robustly optimized bert pretraining approach. arXiv preprint 1907.11692 (2019)."},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/3397271.3401253"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/3178876.3186168"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2020.113297"},{"key":"e_1_3_2_1_32_1","volume-title":"Efficient and robust approximate nearest neighbor search using hierarchical navigable small world graphs","author":"Malkov Yu A","year":"2018","unstructured":"Yu A Malkov and Dmitry A Yashunin. 2018. Efficient and robust approximate nearest neighbor search using hierarchical navigable small world graphs. IEEE transactions on pattern analysis and machine intelligence, Vol. 42, 4 (2018), 824--836."},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/3340531.3412180"},{"key":"e_1_3_2_1_34_1","article-title":"Deep Learning-Based Text Classification","volume":"54","author":"Minaee Shervin","year":"2021","unstructured":"Shervin Minaee, Nal Kalchbrenner, Erik Cambria, Narjes Nikzad, Meysam Chenaghlu, and Jianfeng Gao. 2021. Deep Learning-Based Text Classification: A Comprehensive Review. ACM Comput. Surv., Vol. 54, 3, Article 62 (apr 2021), 40 pages.","journal-title":"A Comprehensive Review. ACM Comput. Surv."},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2022.07.025"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/1341531.1341554"},{"key":"e_1_3_2_1_37_1","volume-title":"Nuts and bolts of building AI applications using Deep Learning. NIPS Keynote Talk","author":"Andrew Ng.","year":"2016","unstructured":"Andrew Ng. 2016. Nuts and bolts of building AI applications using Deep Learning. NIPS Keynote Talk (2016)."},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0262838"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2022.108346"},{"key":"e_1_3_2_1_40_1","volume-title":"a distilled version of BERT: smaller, faster, cheaper and lighter. arXiv preprint arXiv:1910.01108","author":"Sanh Victor","year":"2019","unstructured":"Victor Sanh, Lysandre Debut, Julien Chaumond, and Thomas Wolf. 2019. DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter. arXiv preprint arXiv:1910.01108 (2019)."},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1145\/505282.505283"},{"key":"e_1_3_2_1_42_1","volume-title":"R. Venkatesh Babu, and Vishal M. Patel.","author":"Sindagi Vishwanath A.","year":"2020","unstructured":"Vishwanath A. Sindagi, Rajeev Yasarla, Deepak Sam Babu, R. Venkatesh Babu, and Vishal M. Patel. 2020. Learning to Count in the Crowd from Limited Labeled Data. In Computer Vision -- ECCV. Cham, 212--229."},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ipm.2009.03.002"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1145\/3331184.3331259"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.1972.4309137"},{"key":"e_1_3_2_1_46_1","first-page":"5754","article-title":"XLNet: Generalized Autoregressive Pretraining for Language Understanding","volume":"32","author":"Yang Zhilin","year":"2019","unstructured":"Zhilin Yang, Zihang Dai, Yiming Yang, Jaime Carbonell, Russ R Salakhutdinov, and Quoc V Le. 2019. XLNet: Generalized Autoregressive Pretraining for Language Understanding. In NIPS, Vol. 32. 5754--5764.","journal-title":"NIPS"},{"key":"e_1_3_2_1_47_1","volume-title":"NIPS\u00b416.","author":"Zhang Xiang","unstructured":"Xiang Zhang, Junbo Zhao, and Yann LeCun. 2016. Character-level Convolutional Networks for Text Classification. In NIPS\u00b416. Vol. 28. 649--657."}],"event":{"name":"SIGIR '23: The 46th International ACM SIGIR Conference on Research and Development in Information Retrieval","location":"Taipei Taiwan","acronym":"SIGIR '23","sponsor":["SIGIR ACM Special Interest Group on Information Retrieval"]},"container-title":["Proceedings of the 46th International ACM SIGIR Conference on Research and Development in Information Retrieval"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3539618.3591638","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3539618.3591638","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T17:51:40Z","timestamp":1750182700000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3539618.3591638"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,7,18]]},"references-count":47,"alternative-id":["10.1145\/3539618.3591638","10.1145\/3539618"],"URL":"https:\/\/doi.org\/10.1145\/3539618.3591638","relation":{},"subject":[],"published":{"date-parts":[[2023,7,18]]},"assertion":[{"value":"2023-07-18","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}