{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,21]],"date-time":"2025-09-21T18:19:59Z","timestamp":1758478799660,"version":"3.40.3"},"publisher-location":"Cham","reference-count":37,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031706448"},{"type":"electronic","value":"9783031706455"}],"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_4","type":"book-chapter","created":{"date-parts":[[2024,9,10]],"date-time":"2024-09-10T04:02:14Z","timestamp":1725940934000},"page":"40-54","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Normalized vs Diplomatic Annotation: A Case Study of\u00a0Automatic Information Extraction from\u00a0Handwritten Uruguayan Birth Certificates"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-3606-908X","authenticated-orcid":false,"given":"Natalia","family":"Bottaioli","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6174-9865","authenticated-orcid":false,"given":"Sol\u00e8ne","family":"Tarride","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-3319-6037","authenticated-orcid":false,"given":"J\u00e9r\u00e9my","family":"Anger","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-7774-9217","authenticated-orcid":false,"given":"Seginus","family":"Mowlavi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2465-2014","authenticated-orcid":false,"given":"Marina","family":"Gardella","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7885-903X","authenticated-orcid":false,"given":"Antoine","family":"Tadros","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8855-8513","authenticated-orcid":false,"given":"Gabriele","family":"Facciolo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6309-7116","authenticated-orcid":false,"given":"Rafael Grompone","family":"von Gioi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7508-4080","authenticated-orcid":false,"given":"Christopher","family":"Kermorvant","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6108-897X","authenticated-orcid":false,"given":"Jean-Michel","family":"Morel","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9287-4826","authenticated-orcid":false,"given":"Javier","family":"Preciozzi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,9,11]]},"reference":[{"key":"4_CR1","unstructured":"Dan implementation repository by TEKLIA. https:\/\/gitlab.teklia.com\/atr\/dan, release: 0.2.0rc6"},{"key":"4_CR2","doi-asserted-by":"publisher","unstructured":"Abadie, N., Carlinet, E., Chazalon, J., Dum\u00e9nieu, B.: A benchmark of named entity recognition approaches in historical documents application to 19th century French directories. In: Uchida, S., Barney, E., Eglin, V. (eds) Document Analysis Systems. DAS 2022. Lecture Notes in Computer Science, vol 13237, pp. 445\u2013460. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-06555-2_30","DOI":"10.1007\/978-3-031-06555-2_30"},{"key":"4_CR3","unstructured":"Akbik, A., Bergmann, T., Blythe, D., Rasul, K., Schweter, S., Vollgraf, R.: FLAIR: an easy-to-use framework for state-of-the-art NLP. In: Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics (Demonstrations), pp. 54\u201359 (2019)"},{"key":"4_CR4","doi-asserted-by":"crossref","unstructured":"Arora, A., et\u00a0al.: Using ASR methods for OCR. In: 2019 International Conference on Document Analysis and Recognition (ICDAR), pp. 663\u2013668. IEEE (2019)","DOI":"10.1109\/ICDAR.2019.00111"},{"key":"4_CR5","doi-asserted-by":"crossref","unstructured":"Bluche, T., Louradour, J., Messina, R.: Scan, attend and read: end-to-end handwritten paragraph recognition with MDLSTM attention. In: 2017 14th IAPR International Conference on Document Analysis and Recognition (ICDAR), vol.\u00a01, pp. 1050\u20131055. IEEE (2017)","DOI":"10.1109\/ICDAR.2017.174"},{"key":"4_CR6","doi-asserted-by":"crossref","unstructured":"Boillet, M., Tarride, S., Schneider, Y., Abadie, B., Kesztenbaum, L., Kermorvant, C.: The Socface project: large-scale collection, processing, and analysis of a century of French censuses (2024)","DOI":"10.1007\/978-3-031-70543-4_4"},{"key":"4_CR7","unstructured":"Cheplygina, V., Varoquaux, G.: Artificial intelligence in science: lessons from shortcomings in machine learning for medical imaging. In: Artificial Intelligence in Science: Challenges, Opportunities and the Future of Research. Organization for Economic Co-operation and Development (OECD) (2023)"},{"key":"4_CR8","doi-asserted-by":"crossref","unstructured":"Cl\u00e9rice, T., et\u00a0al.: CATMuS medieval: a multilingual large-scale cross-century dataset in Latin script for handwritten text recognition and beyond (2024)","DOI":"10.1007\/978-3-031-70543-4_11"},{"key":"4_CR9","doi-asserted-by":"publisher","unstructured":"Constum, T. et al.: Recognition and information extraction in historical handwritten tables: toward understanding early 20th century Paris census. In: Uchida, S., Barney, E., Eglin, V. (eds) Document Analysis Systems. DAS 2022. LNCS, vol 13237, pp. 143\u2013157 Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-06555-2_10","DOI":"10.1007\/978-3-031-06555-2_10"},{"issue":"1","key":"4_CR10","doi-asserted-by":"publisher","first-page":"508","DOI":"10.1109\/TPAMI.2022.3144899","volume":"45","author":"D Coquenet","year":"2022","unstructured":"Coquenet, D., Chatelain, C., Paquet, T.: End-to-end handwritten paragraph text recognition using a vertical attention network. IEEE Trans. Pattern Anal. Mach. Intell. 45(1), 508\u2013524 (2022)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"4_CR11","doi-asserted-by":"crossref","unstructured":"Coquenet, D., Chatelain, C., Paquet, T.: DAN: a segmentation-free document attention network for handwritten document recognition. IEEE Trans. Pattern Anal. Mach. Intell. 45(7), 8227\u20138243 (2023)","DOI":"10.1109\/TPAMI.2023.3235826"},{"key":"4_CR12","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)"},{"key":"4_CR13","unstructured":"Graves, A., Schmidhuber, J.: Offline handwriting recognition with multidimensional recurrent neural networks. In: Proceedings of the 21st International Conference on Neural Information Processing Systems, NIPS 2008, pp. 545\u2013552. Curran Associates Inc., Red Hook, NY, USA (2008)"},{"key":"4_CR14","doi-asserted-by":"crossref","unstructured":"Grosicki, E., Carr\u00e9, M., Brodin, J.M., Geoffrois, E.: Results of the RIMES evaluation campaign for handwritten mail processing. In: 2009 10th International Conference on Document Analysis and Recognition, pp. 941\u2013945. IEEE (2009)","DOI":"10.1109\/ICDAR.2009.224"},{"key":"4_CR15","doi-asserted-by":"publisher","unstructured":"Huang, Y., Lv, T., Cui, L., Lu, Y., Wei, F.: LayoutLMv3: pre-training for document AI with unified text and image masking. In: Proceedings of the 30th ACM International Conference on Multimedia, MM 2022, pp. 4083\u20134091. ACM, New York, NY, USA (2022). https:\/\/doi.org\/10.1145\/3503161.3548112","DOI":"10.1145\/3503161.3548112"},{"key":"4_CR16","doi-asserted-by":"publisher","first-page":"498","DOI":"10.1007\/978-3-031-19815-1_29","volume-title":"Comput. Vision - ECCV 2022","author":"G Kim","year":"2022","unstructured":"Kim, G., et al.: OCR-free document understanding transformer. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) Comput. Vision - ECCV 2022, pp. 498\u2013517. Springer Nature Switzerland, Cham (2022)"},{"key":"4_CR17","unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. Adv. Neural Inf. Proc. Syst . 25 (2012)"},{"key":"4_CR18","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.\u00a037, pp. 13094\u201313102 (2023)","DOI":"10.1609\/aaai.v37i11.26538"},{"key":"4_CR19","unstructured":"Mikolov, T., Sutskever, I., Chen, K., Corrado, G.S., Dean, J.: Distributed representations of words and phrases and their compositionality. Adv. Neural Inf. Process. Syst. 26 (2013)"},{"key":"4_CR20","unstructured":"Mikolov, T., Sutskever, I., Chen, K., Corrado, G.S., Dean, J.: Distributed representations of words and phrases and their compositionality. Adv. Neural Inf. Process. Syst. 26 (2013)"},{"key":"4_CR21","doi-asserted-by":"publisher","first-page":"429","DOI":"10.1007\/978-3-031-06555-2_29","volume-title":"Document Analysis Systems: 15th IAPR International Workshop, DAS 2022, La Rochelle, France, May 22\u201325, 2022, Proceedings","author":"CB Monroc","year":"2022","unstructured":"Monroc, C.B., Miret, B., Bonhomme, M.-L., Kermorvant, C.: A comprehensive study of\u00a0open-source libraries for\u00a0named entity recognition on\u00a0handwritten historical documents. In: Uchida, S., Barney, E., Eglin, V. (eds.) Document Analysis Systems: 15th IAPR International Workshop, DAS 2022, La Rochelle, France, May 22\u201325, 2022, Proceedings, pp. 429\u2013444. Springer International Publishing, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-06555-2_29"},{"key":"4_CR22","doi-asserted-by":"crossref","unstructured":"Nion, T., et al.: Handwritten information extraction from historical census documents. In: 2013 12th International Conference on Document Analysis and Recognition, pp. 822\u2013826. IEEE (2013)","DOI":"10.1109\/ICDAR.2013.168"},{"key":"4_CR23","doi-asserted-by":"crossref","unstructured":"Oliveira, S.A., Seguin, B., Kaplan, F.: dhSegment: a generic deep-learning approach for document segmentation. In: 2018 16th International Conference on Frontiers in Handwriting Recognition (ICFHR), pp. 7\u201312. IEEE (2018)","DOI":"10.1109\/ICFHR-2018.2018.00011"},{"key":"4_CR24","doi-asserted-by":"publisher","unstructured":"Peng, Q., et al.: ERNIE-layout: layout knowledge enhanced pre-training for visually-rich document understanding. In: Goldberg, Y., Kozareva, Z., Zhang, Y. (eds.) Findings of the Association for Computational Linguistics: EMNLP 2022, pp. 3744\u20133756. Association for Computational Linguistics, Abu Dhabi, United Arab Emirates (Dec 2022). https:\/\/doi.org\/10.18653\/v1\/2022.findings-emnlp.274, https:\/\/aclanthology.org\/2022.findings-emnlp.274","DOI":"10.18653\/v1\/2022.findings-emnlp.274"},{"issue":"4","key":"4_CR25","doi-asserted-by":"publisher","first-page":"419","DOI":"10.1007\/s10032-023-00428-9","volume":"26","author":"R Petitpierre","year":"2023","unstructured":"Petitpierre, R., Kramer, M., Rappo, L.: An end-to-end pipeline for historical censuses processing. Int. J. Doc. Anal. Recogn. (IJDAR) 26(4), 419\u2013432 (2023)","journal-title":"Int. J. Doc. Anal. Recogn. (IJDAR)"},{"key":"4_CR26","doi-asserted-by":"crossref","unstructured":"Puigcerver, J.: Are multidimensional recurrent layers really necessary for handwritten text recognition? In: 2017 14th IAPR International Conference on Document Analysis and Recognition (ICDAR), vol.\u00a01, pp. 67\u201372. IEEE (2017)","DOI":"10.1109\/ICDAR.2017.20"},{"key":"4_CR27","doi-asserted-by":"crossref","unstructured":"Puigcerver, J.: Are multidimensional recurrent layers really necessary for handwritten text recognition? In: 2017 14th IAPR International Conference on Document Analysis and Recognition (ICDAR), vol.\u00a01, pp. 67\u201372. IEEE (2017)","DOI":"10.1109\/ICDAR.2017.20"},{"key":"4_CR28","doi-asserted-by":"publisher","unstructured":"Romero, V., et al.: The ESPOSALLES database: an ancient marriage license corpus for off-line handwriting recognition. Pattern Recogn. 46(6), 1658\u20131669 (2013). https:\/\/doi.org\/10.1016\/j.patcog.2012.11.024, https:\/\/www.sciencedirect.com\/science\/article\/pii\/S0031320312005080","DOI":"10.1016\/j.patcog.2012.11.024"},{"key":"4_CR29","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"234","DOI":"10.1007\/978-3-319-24574-4_28","volume-title":"Medical Image Computing and Computer-Assisted Intervention \u2013 MICCAI 2015","author":"O Ronneberger","year":"2015","unstructured":"Ronneberger, O., Fischer, P., Brox, T.: U-Net: convolutional networks for biomedical image segmentation. In: Navab, N., Hornegger, J., Wells, W.M., Frangi, A.F. (eds.) MICCAI 2015. LNCS, vol. 9351, pp. 234\u2013241. Springer, Cham (2015). https:\/\/doi.org\/10.1007\/978-3-319-24574-4_28"},{"key":"4_CR30","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"55","DOI":"10.1007\/978-3-030-86334-0_4","volume-title":"Document Analysis and Recognition \u2013 ICDAR 2021","author":"SS Singh","year":"2021","unstructured":"Singh, S.S., Karayev, S.: Full page handwriting recognition via image to sequence extraction. In: Llad\u00f3s, J., Lopresti, D., Uchida, S. (eds.) ICDAR 2021. LNCS, vol. 12823, pp. 55\u201369. Springer, Cham (2021). https:\/\/doi.org\/10.1007\/978-3-030-86334-0_4"},{"key":"4_CR31","doi-asserted-by":"publisher","unstructured":"Tarride, S., Boillet, M., Kermorvant, C.: Key-Value Information Extraction from Full Handwritten Pages. In: Fink, G.A., Jain, R., Kise, K., Zanibbi, R. (eds) Document Analysis and Recognition - ICDAR 2023. ICDAR 2023. LNCS, vol 14188, pp. 185\u2013204 Springer, Cham (2023). https:\/\/doi.org\/10.1007\/978-3-031-41679-8_11","DOI":"10.1007\/978-3-031-41679-8_11"},{"key":"4_CR32","doi-asserted-by":"publisher","first-page":"421","DOI":"10.1007\/978-3-031-41682-8_26","volume-title":"Document Analysis and Recognition - ICDAR 2023: 17th International Conference, San Jos\u00e9, CA, USA, August 21\u201326, 2023, Proceedings, Part III","author":"S Tarride","year":"2023","unstructured":"Tarride, S., Boillet, M., Moufflet, J.-F., Kermorvant, C.: SIMARA: a database for\u00a0key-value information extraction from\u00a0full-page handwritten documents. In: Fink, G.A., Jain, R., Kise, K., Zanibbi, R. (eds.) Document Analysis and Recognition - ICDAR 2023: 17th International Conference, San Jos\u00e9, CA, USA, August 21\u201326, 2023, Proceedings, Part III, pp. 421\u2013437. Springer Nature Switzerland, Cham (2023). https:\/\/doi.org\/10.1007\/978-3-031-41682-8_26"},{"key":"4_CR33","doi-asserted-by":"publisher","first-page":"644","DOI":"10.1007\/978-3-031-06555-2_43","volume-title":"Document Analysis Systems: 15th IAPR International Workshop, DAS 2022, La Rochelle, France, May 22\u201325, 2022, Proceedings","author":"S Tarride","year":"2022","unstructured":"Tarride, S., Lemaitre, A., Co\u00fcasnon, B., Tardivel, S.: A comparative study of information extraction strategies using an attention-based neural network. In: Uchida, S., Barney, E., Eglin, V. (eds.) Document Analysis Systems: 15th IAPR International Workshop, DAS 2022, La Rochelle, France, May 22\u201325, 2022, Proceedings, pp. 644\u2013658. Springer International Publishing, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-06555-2_43"},{"issue":"3","key":"4_CR34","doi-asserted-by":"publisher","first-page":"255","DOI":"10.1007\/s10032-023-00427-w","volume":"26","author":"S Tarride","year":"2023","unstructured":"Tarride, S., et al.: Large-scale genealogical information extraction from handwritten Quebec parish records. Int. J. Doc. Anal. Recogn. (IJDAR) 26(3), 255\u2013272 (2023). https:\/\/doi.org\/10.1007\/s10032-023-00427-w","journal-title":"Int. J. Doc. Anal. Recogn. (IJDAR)"},{"key":"4_CR35","doi-asserted-by":"crossref","unstructured":"Tu, Y., Guo, Y., Chen, H., Tang, J.: LayoutMask: enhance text-layout interaction in multi-modal pre-training for document understanding. In: Annual Meeting of the Association for Computational Linguistics (2023). https:\/\/api.semanticscholar.org\/CorpusID:258967524","DOI":"10.18653\/v1\/2023.acl-long.847"},{"key":"4_CR36","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing System, vol. 30 (2017)"},{"key":"4_CR37","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"372","DOI":"10.1007\/978-3-030-01231-1_23","volume-title":"Computer Vision \u2013 ECCV 2018","author":"C Wigington","year":"2018","unstructured":"Wigington, C., Tensmeyer, C., Davis, B., Barrett, W., Price, B., Cohen, S.: Start, follow, read: end-to-end full-page handwriting recognition. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11210, pp. 372\u2013388. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01231-1_23"}],"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_4","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,27]],"date-time":"2024-11-27T23:04:28Z","timestamp":1732748668000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-70645-5_4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9783031706448","9783031706455"],"references-count":37,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-70645-5_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"}}]}}