{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T01:55:17Z","timestamp":1743040517520,"version":"3.40.3"},"publisher-location":"Cham","reference-count":22,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031704413"},{"type":"electronic","value":"9783031704420"}],"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\/978-3-031-70442-0_15","type":"book-chapter","created":{"date-parts":[[2024,9,10]],"date-time":"2024-09-10T08:09:40Z","timestamp":1725955780000},"page":"244-257","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["How Does Changing the\u00a0Optical Character Recognition System Impact the\u00a0Layout-Aware Named Entity Recognition Models?"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1320-5190","authenticated-orcid":false,"given":"Jo\u00e3o","family":"Macedo","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8327-9734","authenticated-orcid":false,"given":"Byron","family":"Bezerra","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6421-9747","authenticated-orcid":false,"given":"Cleber","family":"Zanchettin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,9,11]]},"reference":[{"key":"15_CR1","unstructured":"Devlin, J., Chang, M., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. CoRR (2018). http:\/\/arxiv.org\/abs\/1810.04805"},{"key":"15_CR2","doi-asserted-by":"publisher","unstructured":"Dosovitskiy, A., et al.: An image is worth $$16 \\times 16$$ words: transformers for image recognition at scale (2020). https:\/\/doi.org\/10.48550\/ARXIV.2010.11929","DOI":"10.48550\/ARXIV.2010.11929"},{"key":"15_CR3","doi-asserted-by":"publisher","first-page":"70","DOI":"10.1108\/EUM0000000007162","volume":"54","author":"R Gaizauskas","year":"1998","unstructured":"Gaizauskas, R., Wilks, Y.: Information extraction: beyond document retrieval. J. Documentation 54, 70\u2013105 (1998)","journal-title":"J. Documentation"},{"key":"15_CR4","unstructured":"Garncarek, L., Powalski, R., Stanislawek, T., Topolski, B., Halama, P., Gralinski, F.: LAMBERT: layout-aware language modeling using BERT for information extraction. CoRR (2020). https:\/\/arxiv.org\/abs\/2002.08087"},{"key":"15_CR5","doi-asserted-by":"publisher","unstructured":"Hamdi, A., Jean-Caurant, A., Sidere, N., Coustaty, M., Doucet, A.: An analysis of the performance of named entity recognition over OCRed documents. In: Proceedings of the 18th Joint Conference on Digital Libraries, JCDL 20919, pp. 333\u2013334. IEEE Press (2020). https:\/\/doi.org\/10.1109\/JCDL.2019.00057","DOI":"10.1109\/JCDL.2019.00057"},{"key":"15_CR6","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"87","DOI":"10.1007\/978-3-030-54956-5_7","volume-title":"Digital Libraries for Open Knowledge","author":"A Hamdi","year":"2020","unstructured":"Hamdi, A., Jean-Caurant, A., Sid\u00e8re, N., Coustaty, M., Doucet, A.: Assessing and minimizing the impact of OCR quality on named entity recognition. In: Hall, M., Mer\u010dun, T., Risse, T., Duchateau, F. (eds.) TPDL 2020. LNCS, vol. 12246, pp. 87\u2013101. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-54956-5_7"},{"key":"15_CR7","doi-asserted-by":"publisher","unstructured":"Hamdi, A., Linhares\u00a0Pontes, E., Sid\u00e8re, N., Coustaty, M., Doucet, A.: In-depth analysis of the impact of OCR errors on named entity recognition and linking. Nat. Lang. Eng. 29(2), 425\u2013448 (2022). https:\/\/doi.org\/10.1017\/S1351324922000110. https:\/\/hal.science\/hal-03615997","DOI":"10.1017\/S1351324922000110"},{"key":"15_CR8","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 (2022). https:\/\/doi.org\/10.48550\/ARXIV.2204.08387","DOI":"10.48550\/ARXIV.2204.08387"},{"key":"15_CR9","doi-asserted-by":"publisher","unstructured":"Kim, W., Son, B., Kim, I.: ViLT: vision-and-language transformer without convolution or region supervision (2021). https:\/\/doi.org\/10.48550\/ARXIV.2102.03334","DOI":"10.48550\/ARXIV.2102.03334"},{"key":"15_CR10","doi-asserted-by":"publisher","unstructured":"Koudoro-Parfait, C., Lejeune, G., Roe, G.: Spatial named entity recognition in literary texts: what is the influence of OCR noise? In: Proceedings of the 5th ACM SIGSPATIAL International Workshop on Geospatial Humanities, GeoHumanities 2021, pp. 13\u201321. Association for Computing Machinery, New York (2021). https:\/\/doi.org\/10.1145\/3486187.3490206","DOI":"10.1145\/3486187.3490206"},{"key":"15_CR11","doi-asserted-by":"publisher","unstructured":"Lewis, D., Agam, G., Argamon, S., Frieder, O., Grossman, D., Heard, J.: Building a test collection for complex document information processing. In: Proceedings of the 29th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR 2006, pp. 665\u2013666. Association for Computing Machinery, New York (2006). https:\/\/doi.org\/10.1145\/1148170.1148307","DOI":"10.1145\/1148170.1148307"},{"key":"15_CR12","doi-asserted-by":"publisher","unstructured":"Li, C., et al.: PP-OCRv3: more attempts for the improvement of ultra lightweight OCR system (2022). https:\/\/doi.org\/10.48550\/ARXIV.2206.03001","DOI":"10.48550\/ARXIV.2206.03001"},{"key":"15_CR13","doi-asserted-by":"crossref","unstructured":"Lin, T., Doll\u00e1r, P., Girshick, R.B., He, K., Hariharan, B., Belongie, S.J.: Feature pyramid networks for object detection. CoRR (2016). http:\/\/arxiv.org\/abs\/1612.03144","DOI":"10.1109\/CVPR.2017.106"},{"key":"15_CR14","unstructured":"Liu, Y., et al.: RoBERTa: a robustly optimized BERT pretraining approach (2019)"},{"key":"15_CR15","unstructured":"Park, S., et al.: Cord: a consolidated receipt dataset for post-OCR parsing (2019)"},{"key":"15_CR16","unstructured":"Paszke, A., et al.: PyTorch: an imperative style, high-performance deep learning library. In: Advances in Neural Information Processing Systems, vol. 32, pp. 8024\u20138035. Curran Associates, Inc. (2019). http:\/\/papers.neurips.cc\/paper\/9015-pytorch-an-imperative-style-high-performance-deep-learning-library.pdf"},{"key":"15_CR17","unstructured":"Vaswani, A., et al.: Attention is all you need. CoRR (2017). http:\/\/arxiv.org\/abs\/1706.03762"},{"key":"15_CR18","doi-asserted-by":"publisher","unstructured":"Wang, J., Jin, L., Ding, K.: Lilt: a simple yet effective language-independent layout transformer for structured document understanding (2022). https:\/\/doi.org\/10.48550\/ARXIV.2202.13669","DOI":"10.48550\/ARXIV.2202.13669"},{"key":"15_CR19","unstructured":"Wolf, T., et al.: Huggingface\u2019s transformers: state-of-the-art natural language processing. CoRR (2019). http:\/\/arxiv.org\/abs\/1910.03771"},{"key":"15_CR20","doi-asserted-by":"publisher","unstructured":"Xie, S., Girshick, R., Dollar, P., Tu, Z., He, K.: Aggregated residual transformations for deep neural networks. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). IEEE (2017). https:\/\/doi.org\/10.1109\/cvpr.2017.634","DOI":"10.1109\/cvpr.2017.634"},{"key":"15_CR21","doi-asserted-by":"crossref","unstructured":"Xu, Y., et al.: LayoutLMv2: multi-modal pre-training for visually-rich document understanding. CoRR (2020). https:\/\/arxiv.org\/abs\/2012.14740","DOI":"10.18653\/v1\/2021.acl-long.201"},{"key":"15_CR22","doi-asserted-by":"crossref","unstructured":"Xu, Y., Li, M., Cui, L., Huang, S., Wei, F., Zhou, M.: LayoutLM: pre-training of text and layout for document image understanding. CoRR (2019). http:\/\/arxiv.org\/abs\/1912.13318","DOI":"10.1145\/3394486.3403172"}],"container-title":["Lecture Notes in Computer Science","Document Analysis Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-70442-0_15","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,10]],"date-time":"2024-09-10T08:15:41Z","timestamp":1725956141000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-70442-0_15"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9783031704413","9783031704420"],"references-count":22,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-70442-0_15","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":"DAS","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Workshop on Document Analysis Systems","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":"31 August 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"16","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"das2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/das2024.seecs.edu.pk\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}