{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T19:37:50Z","timestamp":1743104270543,"version":"3.40.3"},"publisher-location":"Cham","reference-count":16,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031706417"},{"type":"electronic","value":"9783031706424"}],"license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024]]},"DOI":"10.1007\/978-3-031-70642-4_4","type":"book-chapter","created":{"date-parts":[[2024,9,10]],"date-time":"2024-09-10T18:02:18Z","timestamp":1725991338000},"page":"57-70","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Mind the\u00a0Gap:Analyzing Lacunae with\u00a0Transformer-Based Transcription"],"prefix":"10.1007","author":[{"given":"Jaydeep","family":"Borkar","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6636-6940","authenticated-orcid":false,"given":"David A.","family":"Smith","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,9,11]]},"reference":[{"issue":"2","key":"4_CR1","first-page":"59","volume":"33","author":"K Arlitsch","year":"2004","unstructured":"Arlitsch, K., Herbert, J.: Microfilm, paper, and OCR: issues in newspaper digitization. Utah Digit. Newspapers Program 33(2), 59\u201367 (2004)","journal-title":"Utah Digit. Newspapers Program"},{"issue":"7900","key":"4_CR2","doi-asserted-by":"publisher","first-page":"280","DOI":"10.1038\/s41586-022-04448-z","volume":"603","author":"Y Assael","year":"2022","unstructured":"Assael, Y., et al.: Restoring and attributing ancient texts using deep neural networks. Nature 603(7900), 280\u2013283 (2022)","journal-title":"Nature"},{"key":"4_CR3","unstructured":"Baevski, A., Zhou, Y., Mohamed, A., Auli, M.: wav2vec 2.0: A framework for self-supervised learning of speech representations. In: Larochelle, H., Ranzato, M., Hadsell, R., Balcan, M., Lin, H. (eds.) Advances in Neural Information Processing Systems, vol. 33, pp. 12449\u201312460. Curran Associates, Inc. (2020)"},{"key":"4_CR4","unstructured":"Cowen-Breen, C., Brooks, C., Haubold, J., Graziosi, B.: Logion: machine learning for Greek philology. arXiv:2305.01099 [cs] (2023)"},{"key":"4_CR5","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. In: Burstein, J., Doran, C., Solorio, T. (eds.) 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 (2019)"},{"key":"4_CR6","doi-asserted-by":"crossref","unstructured":"Dong, R., Smith, D.: Multi-input attention for unsupervised OCR correction. In: Gurevych, I., Miyao, Y. (eds.) Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 2363\u20132372. Association for Computational Linguistics, Melbourne, Australia (2018)","DOI":"10.18653\/v1\/P18-1220"},{"key":"4_CR7","unstructured":"van Groningen, B.A.: De signis criticis in edendo adhibendis. Mnemosyne 59(4), 362\u2013365 (1932), https:\/\/www.jstor.org\/stable\/4426628"},{"key":"4_CR8","doi-asserted-by":"crossref","unstructured":"H\u00e4m\u00e4l\u00e4inen, M., Hengchen, S.: From the paft to the fiiture: a fully automatic NMT and word embeddings method for OCR post-correction. In: Mitkov, R., Angelova, G. (eds.) Proceedings of the International Conference on Recent Advances in Natural Language Processing (RANLP 2019), pp. 431\u2013436. INCOMA Ltd., Varna, Bulgaria (2019)","DOI":"10.26615\/978-954-452-056-4_051"},{"key":"4_CR9","doi-asserted-by":"crossref","unstructured":"Koenecke, A., Choi, A.S.G., Mei, K., Schellmann, H., Sloane, M.: Careless whisper: speech-to-text hallucination harms. arXiv:2402.08021 [cs] (2024)","DOI":"10.1145\/3630106.3658996"},{"key":"4_CR10","doi-asserted-by":"crossref","unstructured":"Li, M., et al.: TrOCR: transformer-based optical character recognition with pre-trained models. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 37, no. 11, pp. 13094\u201313102 (2023)","DOI":"10.1609\/aaai.v37i11.26538"},{"issue":"7","key":"4_CR11","doi-asserted-by":"publisher","first-page":"148","DOI":"10.1108\/JD-09-2023-0183","volume":"80","author":"J Nockels","year":"2024","unstructured":"Nockels, J., Gooding, P., Terras, M.: The implications of handwritten text recognition for accessing the past at scale. J. Documentation 80(7), 148\u2013167 (2024). https:\/\/doi.org\/10.1108\/JD-09-2023-0183","journal-title":"J. Documentation"},{"key":"4_CR12","first-page":"9","volume":"1","author":"A Radford","year":"2019","unstructured":"Radford, A., Wu, J., Child, R., Luan, D., Amodei, D., Sutskever, I.: Language models are unsupervised multitask learners. OpenAI blog 1, 9 (2019)","journal-title":"OpenAI blog"},{"key":"4_CR13","first-page":"1","volume":"21","author":"C Raffel","year":"2020","unstructured":"Raffel, C., et al.: Exploring the limits of transfer learning with a unified text-to-text transformer. J. Mach. Learn. Res. 21, 1\u201367 (2020)","journal-title":"J. Mach. Learn. Res."},{"key":"4_CR14","doi-asserted-by":"crossref","unstructured":"Rijhwani, S., Anastasopoulos, A., Neubig, G.: OCR post correction for endangered language texts. In: Webber, B., Cohn, T., He, Y., Liu, Y. (eds.) Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pp. 5931\u20135942. Association for Computational Linguistics, Online (2020)","DOI":"10.18653\/v1\/2020.emnlp-main.478"},{"key":"4_CR15","doi-asserted-by":"publisher","first-page":"1285","DOI":"10.1162\/tacl_a_00427","volume":"9","author":"S Rijhwani","year":"2021","unstructured":"Rijhwani, S., Rosenblum, D., Anastasopoulos, A., Neubig, G.: Lexically aware semi-supervised learning for OCR post-correction. Trans. Assoc. Comput. Linguist. 9, 1285\u20131302 (2021)","journal-title":"Trans. Assoc. Comput. Linguist."},{"key":"4_CR16","doi-asserted-by":"publisher","first-page":"206","DOI":"10.18653\/v1\/2022.findings-naacl.15","volume-title":"Findings of the Association for Computational Linguistics: NAACL 2022","author":"N Vogler","year":"2022","unstructured":"Vogler, N., Allen, J., Miller, M., Berg-Kirkpatrick, T.: Lacuna reconstruction: self-supervised pre-training for low-resource historical document transcription. In: Carpuat, M., de Marneffe, M.C., Meza Ruiz, I.V. (eds.) Findings of the Association for Computational Linguistics: NAACL 2022, pp. 206\u2013216. Association for Computational Linguistics, Seattle, United States (Jul (2022)"}],"container-title":["Lecture Notes in Computer Science","Document Analysis and Recognition \u2013 ICDAR 2024 Workshops"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-70642-4_4","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,10]],"date-time":"2024-09-10T18:03:02Z","timestamp":1725991382000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-70642-4_4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9783031706417","9783031706424"],"references-count":16,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-70642-4_4","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024]]},"assertion":[{"value":"11 September 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICDAR","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Document Analysis and Recognition","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Athens","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Greece","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"30 August 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 September 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icdar2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/icdar2024.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}