{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,4]],"date-time":"2026-09-04T18:36:03Z","timestamp":1788546963437,"version":"build-2803163510"},"publisher-location":"Cham","reference-count":23,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031194955","type":"print"},{"value":"9783031194962","type":"electronic"}],"license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"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":[[2022]]},"DOI":"10.1007\/978-3-031-19496-2_13","type":"book-chapter","created":{"date-parts":[[2022,10,22]],"date-time":"2022-10-22T05:03:19Z","timestamp":1666414999000},"page":"163-177","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Evaluating the\u00a0Impact of\u00a0OCR Quality on\u00a0Short Texts Classification Task"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3812-7245","authenticated-orcid":false,"given":"Oxana","family":"Vitman","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8104-5141","authenticated-orcid":false,"given":"Yevhen","family":"Kostiuk","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4718-820X","authenticated-orcid":false,"given":"Paul","family":"Plachinda","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1975-303X","authenticated-orcid":false,"given":"Alisa","family":"Zhila","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3901-3522","authenticated-orcid":false,"given":"Grigori","family":"Sidorov","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7845-9039","authenticated-orcid":false,"given":"Alexander","family":"Gelbukh","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2022,10,23]]},"reference":[{"key":"13_CR1","doi-asserted-by":"crossref","unstructured":"Alex, B., Burns, J.: Estimating and rating the quality of optically character recognised text. In: Proceedings of the First International Conference on Digital Access to Textual Cultural Heritage, pp. 97\u2013102 (2014)","DOI":"10.1145\/2595188.2595214"},{"key":"13_CR2","unstructured":"Alex, B., Grover, C., Klein, E., Tobin, R.: Digitised historical text: does it have to be mediocre? In: KONVENS, pp. 401\u2013409 (2012)"},{"key":"13_CR3","doi-asserted-by":"publisher","unstructured":"Amjad, M., et al.: Urduthreat@ fire2021: shared track on abusive threat identification in Urdu. In: Forum for Information Retrieval Evaluation, pp. 9\u201311. FIRE 2021, Association for Computing Machinery, New York, NY, USA (2021). https:\/\/doi.org\/10.1145\/3503162.3505241","DOI":"10.1145\/3503162.3505241"},{"key":"13_CR4","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":"13_CR5","doi-asserted-by":"crossref","unstructured":"Briskilal, J., Subalalitha, C.: An ensemble model for classifying idioms and literal texts using BERT and RoBERTa. Inf. Process. Manage. 59(1), 102756 (2022)","DOI":"10.1016\/j.ipm.2021.102756"},{"key":"13_CR6","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, Volume 1 (Long and Short Papers), pp. 4171\u20134186. Association for Computational Linguistics, Minneapolis, Minnesota, June 2019. https:\/\/doi.org\/10.18653\/v1\/N19-1423","DOI":"10.18653\/v1\/N19-1423"},{"key":"13_CR7","unstructured":"Guo, Y., Dong, X., Al-Garadi, M.A., Sarker, A., Paris, C., Aliod, D.M.: Benchmarking of transformer-based pre-trained models on social media text classification datasets. In: Proceedings of the The 18th Annual Workshop of the Australasian Language Technology Association, pp. 86\u201391. Australasian Language Technology Association, Virtual Workshop, December 2020. https:\/\/aclanthology.org\/2020.alta-1.10"},{"key":"13_CR8","doi-asserted-by":"publisher","unstructured":"Jiang, H., He, P., Chen, W., Liu, X., Gao, J., Zhao, T.: SMART: Robust and efficient fine-tuning for pre-trained natural language models through principled regularized optimization. In: Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pp. 2177\u20132190. Association for Computational Linguistics, July 2020. https:\/\/doi.org\/10.18653\/v1\/2020.acl-main.197, https:\/\/aclanthology.org\/2020.acl-main.197","DOI":"10.18653\/v1\/2020.acl-main.197"},{"key":"13_CR9","doi-asserted-by":"crossref","unstructured":"Joulin, A., Grave, E., Bojanowski, P., Mikolov, T.: Bag of tricks for efficient text classification. arXiv preprint arXiv:1607.01759 (2016)","DOI":"10.18653\/v1\/E17-2068"},{"key":"13_CR10","unstructured":"Kim, Y.: Convolutional neural networks for sentence classification. In: Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing, EMNLP 2014, 25\u201329 October 2014, Doha, Qatar, A meeting of SIGDAT, a Special Interest Group of the ACL, pp. 1746\u20131751 (2014). https:\/\/aclweb.org\/anthology\/D\/D14\/D14-1181.pdf"},{"key":"13_CR11","unstructured":"Liu, Y., et al.: RoBERTa: a robustly optimized BERT pretraining approach (2019). arxiv.org\/abs\/1907.11692"},{"key":"13_CR12","unstructured":"Mieskes, M., Schmunk, S.: OCR quality and NLP preprocessing. In: WNLP@ ACL, pp. 102\u2013105 (2019)"},{"key":"13_CR13","unstructured":"Murarka, A., Radhakrishnan, B., Ravichandran, S.: Classification of mental illnesses on social media using RoBERTa. In: Proceedings of the 12th International Workshop on Health Text Mining and Information Analysis, pp. 59\u201368. Association for Computational Linguistics, April 2021. https:\/\/aclanthology.org\/2021.louhi-1.7"},{"key":"13_CR14","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"506","DOI":"10.1007\/11669487_45","volume-title":"Document Analysis Systems VII","author":"M Murata","year":"2006","unstructured":"Murata, M., Busagala, L.S.P., Ohyama, W., Wakabayashi, T., Kimura, F.: The impact of OCR accuracy and feature transformation on automatic text classification. In: Bunke, H., Spitz, A.L. (eds.) DAS 2006. LNCS, vol. 3872, pp. 506\u2013517. Springer, Heidelberg (2006). https:\/\/doi.org\/10.1007\/11669487_45"},{"key":"13_CR15","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":"13_CR16","unstructured":"Smith, D.A., Cordell, R.: A research agenda for historical and multilingual optical character recognition, p. 36. NULab, Northeastern University (2018). https:\/\/ocr.northeastern.edu\/report"},{"key":"13_CR17","doi-asserted-by":"crossref","unstructured":"Stein, S.S., Argamon, S., Frieder, O.: The effect of OCR errors on stylistic text classification. In: Proceedings of the 29th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, pp. 701\u2013702 (2006)","DOI":"10.1145\/1148170.1148325"},{"key":"13_CR18","doi-asserted-by":"crossref","unstructured":"Van Strien, D., Beelen, K., Ardanuy, M.C., Hosseini, K., McGillivray, B., Colavizza, G.: Assessing the impact of OCR quality on downstream NLP tasks (2020)","DOI":"10.5220\/0009169004840496"},{"key":"13_CR19","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Guyon, I., et al. (eds.) Advances in Neural Information Processing Systems, vol. 30. Curran Associates, Inc. (2017). https:\/\/proceedings.neurips.cc\/paper\/2017\/file\/3f5ee243547dee91fbd053c1c4a845aa-Paper.pdf"},{"key":"13_CR20","doi-asserted-by":"publisher","unstructured":"Wolf, T., et al.: Transformers: state-of-the-art natural language processing. In: Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing: System Demonstrations, pp. 38\u201345. Association for Computational Linguistics, October 2020. https:\/\/doi.org\/10.18653\/v1\/2020.emnlp-demos.6, https:\/\/aclanthology.org\/2020.emnlp-demos.6","DOI":"10.18653\/v1\/2020.emnlp-demos.6"},{"key":"13_CR21","unstructured":"Zhang, Y., Wallace, B.: A sensitivity analysis of (and practitioners\u2019 guide to) convolutional neural networks for sentence classification. arXiv preprint arXiv:1510.03820 (2015)"},{"key":"13_CR22","unstructured":"Zhao, Z., Zhang, Z., Hopfgartner, F.: SS-BERT: mitigating identity terms bias in toxic comment classification by utilising the notion of \u201csubjectivity\u201d and \u201cidentity terms\u201d. CoRR abs\/2109.02691 (2021). arxiv.org\/abs:2109.02691"},{"key":"13_CR23","doi-asserted-by":"publisher","unstructured":"Zhu, Y., et al.: Aligning books and movies: Towards story-like visual explanations by watching movies and reading books. In: 2015 IEEE International Conference on Computer Vision (ICCV), pp. 19\u201327 (2015). https:\/\/doi.org\/10.1109\/ICCV.2015.11","DOI":"10.1109\/ICCV.2015.11"}],"container-title":["Lecture Notes in Computer Science","Advances in Computational Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-19496-2_13","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,10,22]],"date-time":"2022-10-22T07:11:14Z","timestamp":1666422674000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-19496-2_13"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031194955","9783031194962"],"references-count":23,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-19496-2_13","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022]]},"assertion":[{"value":"23 October 2022","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"MICAI","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Mexican International Conference on Artificial Intelligence","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Monterrey","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Mexico","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"24 October 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 October 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"21","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"micai2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.micai.org\/2022\/","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":"137","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":"63","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":"46% - 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","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":"17 External reviewers","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)"}}]}}