{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,17]],"date-time":"2026-05-17T00:13:35Z","timestamp":1778976815208,"version":"3.51.4"},"publisher-location":"Cham","reference-count":36,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031706448","type":"print"},{"value":"9783031706455","type":"electronic"}],"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\/978-3-031-70645-5_2","type":"book-chapter","created":{"date-parts":[[2024,9,10]],"date-time":"2024-09-10T04:02:14Z","timestamp":1725940934000},"page":"12-26","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["TrOCR Meets Language Models: An End-to-End Post-correction Approach"],"prefix":"10.1007","author":[{"given":"Yung-Hsin","family":"Chen","sequence":"first","affiliation":[]},{"given":"Phillip B.","family":"Str\u00f6bel","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,9,11]]},"reference":[{"issue":"1","key":"2_CR1","doi-asserted-by":"publisher","first-page":"49","DOI":"10.21248\/jlcl.33.2018.218","volume":"33","author":"C Amrhein","year":"2018","unstructured":"Amrhein, C., Clematide, S.: Supervised OCR error detection and correction using statistical and neural machine translation methods. J. Lang. Technol. Comput. Linguist. (JLCL) 33(1), 49\u201376 (2018)","journal-title":"J. Lang. Technol. Comput. Linguist. (JLCL)"},{"issue":"3","key":"2_CR2","doi-asserted-by":"publisher","first-page":"1117","DOI":"10.3390\/app10031117","volume":"10","author":"B Belay","year":"2020","unstructured":"Belay, B., Habtegebrial, T., Meshesha, M., Liwicki, M., Belay, G., Stricker, D.: Amharic OCR: an end-to-end learning. Appl. Sci. 10(3), 1117 (2020)","journal-title":"Appl. Sci."},{"key":"2_CR3","doi-asserted-by":"crossref","unstructured":"Breuel, T.M., Ul-Hasan, A., Al-Azawi, M.A., Shafait, F.: High-performance OCR for printed English and Fraktur using LSTM networks. In: 2013 12th International Conference on Document Analysis and Recognition, pp. 683\u2013687. IEEE (2013)","DOI":"10.1109\/ICDAR.2013.140"},{"key":"2_CR4","unstructured":"Chen, Y.H., Zhou, Y.: Enhancing OCR Performance Through Post-OCR Models: Adopting Glyph Embedding for Improved Correction. arXiv preprint arXiv:2308.15262 (2023)"},{"key":"2_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 (2019)"},{"key":"2_CR6","unstructured":"Dosovitskiy, A., et al.: An image is worth 16x16 words: transformers for image recognition at scale. In: International Conference on Learning Representations (2021)"},{"key":"2_CR7","doi-asserted-by":"crossref","unstructured":"Ehrmann, M., Hamdi, A., Pontes, E.L., Romanello, M., Doucet, A.: Named entity recognition and classification in historical documents: a survey. ACM Comput. Surv. 56(2), 1\u201347 (2023)","DOI":"10.1145\/3604931"},{"issue":"7","key":"2_CR8","doi-asserted-by":"publisher","first-page":"934","DOI":"10.1016\/j.patrec.2011.09.009","volume":"33","author":"A Fischer","year":"2012","unstructured":"Fischer, A., Keller, A., Frinken, V., Bunke, H.: Lexicon-free handwritten word spotting using character HMMs. Pattern Recogn. Lett. 33(7), 934\u2013942 (2012)","journal-title":"Pattern Recogn. Lett."},{"key":"2_CR9","doi-asserted-by":"crossref","unstructured":"Huang, J.: A multiplexed network for end-to-end, multilingual OCR. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4547\u20134557 (2021)","DOI":"10.1109\/CVPR46437.2021.00452"},{"key":"2_CR10","unstructured":"Huber, M., Nissel, M., Puga, K.: Old bailey corpus 2.0. hdl:11858\/00-246C-0000-0023-8CFB-2, Licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License (2016)"},{"key":"2_CR11","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2020.107790","volume":"112","author":"L Kang","year":"2021","unstructured":"Kang, L., Riba, P., Villegas, M., Forn\u00e9s, A., Rusi\u00f1ol, M.: Candidate fusion: integrating language modelling into a sequence-to-sequence handwritten word recognition architecture. Pattern Recogn. 112, 107790 (2021)","journal-title":"Pattern Recogn."},{"key":"2_CR12","unstructured":"Karthick, K., Ravindrakumar, K.B., Francis, R., Ilankannan, S.: Steps involved in text recognition and recent research in OCR; a study. Int. J. Recent Technol. Eng. 8(1), 2277\u20133878 (2019)"},{"key":"2_CR13","doi-asserted-by":"crossref","unstructured":"Karthikeyan, S., de Herrera, A.G.S., Doctor, F., Mirza, A.: An OCR post-correction approach using deep learning for processing medical reports. IEEE Trans. Circuits Syst. Video Technol. 32(5), 2574\u20132581 (2021)","DOI":"10.1109\/TCSVT.2021.3087641"},{"key":"2_CR14","doi-asserted-by":"crossref","unstructured":"Karthikeyan, S., de Herrera, A.G.S., Doctor, F., Mirza, A.: An OCR post-correction approach using deep learning for processing medical reports. IEEE Trans. Circuits Syst. Video Technol. 32(5), 2574\u20132581 (2021)","DOI":"10.1109\/TCSVT.2021.3087641"},{"key":"2_CR15","unstructured":"Kettunen, K., Keskustalo, H., Kumpulainen, S., P\u00e4\u00e4kk\u00f6nen, T., Rautiainen, J.: OCR quality affects perceived usefulness of historical newspaper clippings - a user study. In: Proceedings of the 18th Italian Research Conference on Digital Libraries (IRCDL 2022), CEUR-WS.org, Padova, Italy, CEUR Workshop Proceedings (2022)"},{"key":"2_CR16","unstructured":"Kinga, D., Adam, J.B.: A method for stochastic optimization. CoRR, abs\/1412.6980 (2014)"},{"key":"2_CR17","doi-asserted-by":"crossref","unstructured":"Kurar Barakat, B., Cohen, R., Droby, A., Rabaev, I., El-Sana, J.: Learning-free text line segmentation for historical handwritten documents. Appl. Sci. 10(22), 8276 (2020)","DOI":"10.3390\/app10228276"},{"key":"2_CR18","unstructured":"Kyt\u00f6, M. and Culpeper, J.: A corpus of english dialogues 1560-1760 (CED), Literary and Linguistic Data Service (2006)"},{"key":"2_CR19","first-page":"13094","volume":"37","author":"M Li","year":"2023","unstructured":"Li, M., et al.: TrOCR: transformer-based optical character recognition with pre-trained models. In Proc. AAAI Conf. Artif. Intell. 37, 13094\u201313102 (2023)","journal-title":"In Proc. AAAI Conf. Artif. Intell."},{"key":"2_CR20","unstructured":"Literary and Linguistic\u00a0Data Service. The lampeter corpus of Early Modern English tracts. Literary and Linguistic Data Service"},{"key":"2_CR21","unstructured":"Literary and Linguistic\u00a0Data Service. Pamphlets of the American revolution : [selections]\/edited by bernard bailyn. Literary and Linguistic Data Service (1994)"},{"key":"2_CR22","unstructured":"Literary and Linguistic\u00a0Data Service. The english language of the north-west in the late modern english period: a corpus of late 18c prose. Literary and Linguistic Data Service (2003)"},{"key":"2_CR23","unstructured":"Liu, W., Chen, C., Wong, K.Y.K., Su, Z., Han, J.: Star-net: a spatial attention residue network for scene text recognition. In: BMVC, vol. 2, p. 7 (2016)"},{"key":"2_CR24","unstructured":"Liu, Y., et al.: Roberta: a robustly optimized BERT pretraining approach. arXiv preprint arXiv:1907.11692 (2019)"},{"key":"2_CR25","doi-asserted-by":"crossref","unstructured":"Ma, W., Cui, Y., Si, C., Liu, T., Wang, S., Hu, G.: CharBERT: character-aware pre-trained language model. In: Scott, D., Bel, N., Zong, C., (eds) In: Proceedings of the 28th International Conference on Computational Linguistics, pp. 39\u201350, Barcelona, Spain , December 2020. International Committee on Computational Linguistics","DOI":"10.18653\/v1\/2020.coling-main.4"},{"key":"2_CR26","doi-asserted-by":"crossref","unstructured":"Mokhtar, K., Bukhari, S.S., Dengel, A.: OCR error correction: State-of-the-art vs an NMT-based approach. In 2018 13th IAPR International Workshop on Document Analysis Systems (DAS), pp. 429\u2013434. IEEE (2018)","DOI":"10.1109\/DAS.2018.63"},{"key":"2_CR27","doi-asserted-by":"crossref","unstructured":"Neudecker, C.,et al.: OCR-D: an end-to-end open source OCR framework for historical printed documents. In: Proceedings of the 3rd International Conference on Digital Access to Textual Cultural Heritage, pp. 53\u201358 (2019)","DOI":"10.1145\/3322905.3322917"},{"key":"2_CR28","unstructured":"Nevalainen, T.: Parsed corpus of early english correspondence (PCEEC). Literary and Linguistic Data Service (2006)"},{"issue":"6","key":"2_CR29","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3453476","volume":"54","author":"TTH Nguyen","year":"2021","unstructured":"Nguyen, T.T.H., Jatowt, A., Coustaty, M., Doucet, A.: Survey of post-OCR processing approaches. ACM Comput. Surv. (CSUR) 54(6), 1\u201337 (2021)","journal-title":"ACM Comput. Surv. (CSUR)"},{"key":"2_CR30","unstructured":"Schaefer, J., Litvine, A.: Joseph hooker HTR model (June 2023)"},{"key":"2_CR31","doi-asserted-by":"crossref","unstructured":"Sennrich, R., Haddow, B., Birch, A.: Neural machine translation of rare words with subword units. In Erk, K., Smith, N.A. (eds), Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics, Vol. 1, pp. 1715\u20131725, Berlin, Germany. Association for Computational Linguistics (2016)","DOI":"10.18653\/v1\/P16-1162"},{"issue":"9","key":"2_CR32","doi-asserted-by":"publisher","first-page":"2035","DOI":"10.1109\/TPAMI.2018.2848939","volume":"41","author":"B Shi","year":"2018","unstructured":"Shi, B., Yang, M., Wang, X., Lyu, P., Yao, C., Bai, X.: ASTER: an attentional scene text recognizer with flexible rectification. IEEE Trans. Pattern Anal. Mach. Intell. 41(9), 2035\u20132048 (2018)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"3","key":"2_CR33","doi-asserted-by":"publisher","first-page":"314","DOI":"10.7763\/IJMLC.2012.V2.137","volume":"2","author":"A Singh","year":"2012","unstructured":"Singh, A., Bacchuwar, K., Bhasin, A.: A survey of OCR applications. Int. J. Mach. Learn. Comput. 2(3), 314 (2012)","journal-title":"Int. J. Mach. Learn. Comput."},{"key":"2_CR34","doi-asserted-by":"crossref","unstructured":"Str\u00f6bel, P.B., Hodel, T., Boente, W., Volk, M.: The adaptability of a transformer-based OCR model for historical documents. In: Document Analysis and Recognition - ICDAR 2023 Workshops: San Jos\u00e9, CA, USA, 24-26 August 2023, Proceedings, Part I, pp. 34\u201348 (2023)","DOI":"10.1007\/978-3-031-41498-5_3"},{"key":"2_CR35","unstructured":"Vaswani, A.,et al.: Attention is all you need. In: Advances in Neural Information Processing Systems, vol. 30 (2017)"},{"key":"2_CR36","doi-asserted-by":"crossref","unstructured":"Zhang, H., Liu, D., Xiong, Z.: CNN-based text image super-resolution tailored for OCR. In 2017 IEEE Visual Communications and Image Processing (VCIP), pp. 1\u20134. IEEE (2017)","DOI":"10.1109\/VCIP.2017.8305107"}],"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\/978-3-031-70645-5_2","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,10]],"date-time":"2024-09-10T04:09:08Z","timestamp":1725941348000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-70645-5_2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9783031706448","9783031706455"],"references-count":36,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-70645-5_2","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"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":"The authors declare that there are no conflicts of interest regarding the publication of this paper. This research received no specific grant from funding agencies in the public, commercial, or not-for-profit sectors. The views and opinions expressed in this paper are those of the authors and do not necessarily reflect the official policy or position of any affiliated agency of the authors.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Disclosure of Interests"}},{"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"}}]}}