{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,9]],"date-time":"2025-09-09T21:00:11Z","timestamp":1757451611737,"version":"3.40.3"},"publisher-location":"Cham","reference-count":38,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031416811"},{"type":"electronic","value":"9783031416828"}],"license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"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":[[2023]]},"DOI":"10.1007\/978-3-031-41682-8_18","type":"book-chapter","created":{"date-parts":[[2023,8,18]],"date-time":"2023-08-18T07:02:59Z","timestamp":1692342179000},"page":"280-294","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Information Redundancy and\u00a0Biases in\u00a0Public Document Information Extraction Benchmarks"],"prefix":"10.1007","author":[{"given":"Seif","family":"Laatiri","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Pirashanth","family":"Ratnamogan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jo\u00ebl","family":"Tang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Laurent","family":"Lam","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"William","family":"Vanhuffel","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fabien","family":"Caspani","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,8,19]]},"reference":[{"key":"18_CR1","doi-asserted-by":"crossref","unstructured":"Appalaraju, S., Jasani, B., Kota, B.U., Xie, Y., Manmatha, R.: Docformer: end-to-end transformer for document understanding. CoRR abs\/2106.11539 (2021). https:\/\/arxiv.org\/abs\/2106.11539","DOI":"10.1109\/ICCV48922.2021.00103"},{"key":"18_CR2","unstructured":"Arpit, D., et al.: A closer look at memorization in deep networks. In: International Conference on Machine Learning, pp. 233\u2013242. PMLR (2017)"},{"key":"18_CR3","doi-asserted-by":"publisher","first-page":"61","DOI":"10.1016\/j.csl.2017.01.012","volume":"44","author":"I Augenstein","year":"2017","unstructured":"Augenstein, I., Derczynski, L., Bontcheva, K.: Generalisation in named entity recognition: a quantitative analysis. Comput. Speech Lang. 44, 61\u201383 (2017)","journal-title":"Comput. Speech Lang."},{"key":"18_CR4","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) (2019). https:\/\/aclanthology.org\/N19-1423.pdf"},{"key":"18_CR5","unstructured":"Dosovitskiy, A., et al.: An image is worth 16x16 words: transformers for image recognition at scale (2020). https:\/\/arxiv.org\/abs\/2010.11929"},{"key":"18_CR6","doi-asserted-by":"publisher","unstructured":"Gururangan, S., Swayamdipta, S., Levy, O., Schwartz, R., Bowman, S., Smith, N.A.: Annotation artifacts in natural language inference data. In: Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 2 (Short Papers), pp. 107\u2013112. Association for Computational Linguistics, New Orleans, Louisiana, June 2018. https:\/\/doi.org\/10.18653\/v1\/N18-2017, https:\/\/aclanthology.org\/N18-2017","DOI":"10.18653\/v1\/N18-2017"},{"key":"18_CR7","doi-asserted-by":"publisher","unstructured":"Hao, L., Gao, L., Yi, X., Tang, Z.: A table detection method for pdf documents based on convolutional neural networks. In: 2016 12th IAPR Workshop on Document Analysis Systems (DAS), pp. 287\u2013292 (2016). https:\/\/doi.org\/10.1109\/DAS.2016.23","DOI":"10.1109\/DAS.2016.23"},{"key":"18_CR8","doi-asserted-by":"crossref","unstructured":"Harley, A.W., Ufkes, A., Derpanis, K.G.: Evaluation of deep convolutional nets for document image classification and retrieval. CoRR abs\/1502.07058 (2015). http:\/\/arxiv.org\/abs\/1502.07058","DOI":"10.1109\/ICDAR.2015.7333910"},{"key":"18_CR9","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. Association for Computing Machinery, New York, NY, USA (2022). https:\/\/doi.org\/10.1145\/3503161.3548112","DOI":"10.1145\/3503161.3548112"},{"key":"18_CR10","doi-asserted-by":"crossref","unstructured":"Huang, Z., et al.: Icdar 2019 competition on scanned receipt OCR and information extraction, pp. 1516\u20131520 (2019). https:\/\/arxiv.org\/pdf\/2103.10213.pdf","DOI":"10.1109\/ICDAR.2019.00244"},{"key":"18_CR11","doi-asserted-by":"publisher","unstructured":"Jaume, G., Kemal Ekenel, H., Thiran, J.P.: Funsd: a dataset for form understanding in noisy scanned documents. In: 2019 International Conference on Document Analysis and Recognition Workshops (ICDARW), vol. 2, pp. 1\u20136 (2019). https:\/\/doi.org\/10.1109\/ICDARW.2019.10029","DOI":"10.1109\/ICDARW.2019.10029"},{"key":"18_CR12","doi-asserted-by":"crossref","unstructured":"Kim, G., et al.: Ocr-free document understanding transformer (2022)","DOI":"10.1007\/978-3-031-19815-1_29"},{"key":"18_CR13","unstructured":"Kim, W., Son, B., Kim, I.: Vilt: vision-and-language transformer without convolution or region supervision (2021). https:\/\/arxiv.org\/abs\/2102.03334"},{"key":"18_CR14","unstructured":"Lan, Z., Chen, M., Goodman, S., Gimpel, K., Sharma, P., Soricut, R.: Albert: a lite bert for self-supervised learning of language representations. arXiv preprint arXiv:1909.11942 (2019)"},{"key":"18_CR15","unstructured":"Lee, K., et al.: Pix2struct: screenshot parsing as pretraining for visual language understanding (2022)"},{"key":"18_CR16","doi-asserted-by":"crossref","unstructured":"Liu, X., Gao, F., Zhang, Q., Zhao, H.: Graph convolution for multimodal information extraction from visually rich documents. In: NAACL (2019)","DOI":"10.18653\/v1\/N19-2005"},{"key":"18_CR17","doi-asserted-by":"publisher","unstructured":"Liu, Y., et al.: Roberta: a robustly optimized bert pretraining approach (2019). https:\/\/doi.org\/10.48550\/ARXIV.1907.11692, https:\/\/arxiv.org\/abs\/1907.11692","DOI":"10.48550\/ARXIV.1907.11692"},{"key":"18_CR18","unstructured":"Mathew, M., Karatzas, D., Manmatha, R., Jawahar, C.V.: Docvqa: a dataset for VQA on document images. CoRR abs\/2007.00398 (2020). https:\/\/arxiv.org\/abs\/2007.00398"},{"key":"18_CR19","doi-asserted-by":"publisher","unstructured":"Mghabbar, I., Ratnamogan, P.: Building a multi-domain neural machine translation model using knowledge distillation. In: Giacomo, G.D., et al. (eds.) ECAI 2020\u201324th European Conference on Artificial Intelligence, 29 August-8 September 2020, Santiago de Compostela, Spain, August 29 - September 8, 2020 - Including 10th Conference on Prestigious Applications of Artificial Intelligence (PAIS 2020), Frontiers in Artificial Intelligence and Applications, vol. 325, pp. 2116\u20132123. IOS Press (2020). https:\/\/doi.org\/10.3233\/FAIA200335","DOI":"10.3233\/FAIA200335"},{"key":"18_CR20","doi-asserted-by":"crossref","unstructured":"Moosavi, N.S., Strube, M.: Using linguistic features to improve the generalization capability of neural coreference resolvers. arXiv preprint arXiv:1708.00160 (2017)","DOI":"10.18653\/v1\/D18-1018"},{"key":"18_CR21","unstructured":"Park, S., et al.: Cord: a consolidated receipt dataset for post-ocr parsing (2019)"},{"key":"18_CR22","unstructured":"Pradhan, S., Moschitti, A., Xue, N., Uryupina, O., Zhang, Y.: Conll-2012 shared task: modeling multilingual unrestricted coreference in ontonotes. In: Joint Conference on EMNLP and CoNLL-Shared Task, pp. 1\u201340 (2012)"},{"key":"18_CR23","unstructured":"Ramshaw, L., Marcus, M.: Text chunking using transformation-based learning. In: Third Workshop on Very Large Corpora (1995). https:\/\/aclanthology.org\/W95-0107"},{"key":"18_CR24","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster r-cnn: towards real-time object detection with region proposal networks. In: Cortes, C., Lawrence, N., Lee, D., Sugiyama, M., Garnett, R. (eds.) Advances in Neural Information Processing Systems, vol. 28. Curran Associates, Inc. (2015). https:\/\/proceedings.neurips.cc\/paper\/2015\/file\/14bfa6bb14875e45bba028a21ed38046-Paper.pdf"},{"key":"18_CR25","unstructured":"Sang, E.F., De Meulder, F.: Introduction to the conll-2003 shared task: language-independent named entity recognition. arXiv preprint cs\/0306050 (2003)"},{"key":"18_CR26","doi-asserted-by":"publisher","unstructured":"Schreiber, S., Agne, S., Wolf, I., Dengel, A., Ahmed, S.: Deepdesrt: deep learning for detection and structure recognition of tables in document images. In: 2017 14th IAPR International Conference on Document Analysis and Recognition (ICDAR), vol. 01, pp. 1162\u20131167 (2017). https:\/\/doi.org\/10.1109\/ICDAR.2017.192","DOI":"10.1109\/ICDAR.2017.192"},{"key":"18_CR27","doi-asserted-by":"publisher","unstructured":"Soto, C., Yoo, S.: Visual detection with context for document layout analysis. In: Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), pp. 3464\u20133470. Association for Computational Linguistics, Hong Kong, China, November 2019. https:\/\/doi.org\/10.18653\/v1\/D19-1348, https:\/\/aclanthology.org\/D19-1348","DOI":"10.18653\/v1\/D19-1348"},{"key":"18_CR28","unstructured":"Stanislawek, T., et al.: Kleister: key information extraction datasets involving long documents with complex layouts. CoRR abs\/2105.05796 (2021). https:\/\/arxiv.org\/abs\/2105.05796"},{"key":"18_CR29","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"383","DOI":"10.1007\/978-3-030-45442-5_48","volume-title":"Advances in Information Retrieval","author":"B Taill\u00e9","year":"2020","unstructured":"Taill\u00e9, B., Guigue, V., Gallinari, P.: Contextualized embeddings in named-entity recognition: an empirical study on generalization. In: Jose, J.M., et al. (eds.) ECIR 2020. LNCS, vol. 12036, pp. 383\u2013391. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-45442-5_48"},{"key":"18_CR30","doi-asserted-by":"publisher","unstructured":"Toshniwal, S., Xia, P., Wiseman, S., Livescu, K., Gimpel, K.: On generalization in coreference resolution. In: Proceedings of the Fourth Workshop on Computational Models of Reference, Anaphora and Coreference, pp. 111\u2013120. Association for Computational Linguistics, Punta Cana, Dominican Republic, November 2021. https:\/\/doi.org\/10.18653\/v1\/2021.crac-1.12, https:\/\/aclanthology.org\/2021.crac-1.12","DOI":"10.18653\/v1\/2021.crac-1.12"},{"key":"18_CR31","unstructured":"Vu, H.M., Nguyen, D.T.: Revising FUNSD dataset for key-value detection in document images. CoRR abs\/2010.05322 (2020), https:\/\/arxiv.org\/abs\/2010.05322"},{"key":"18_CR32","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, https:\/\/arxiv.org\/abs\/2202.13669","DOI":"10.48550\/ARXIV.2202.13669"},{"key":"18_CR33","doi-asserted-by":"crossref","unstructured":"Wang, J., Jin, L., Ding, K.: Lilt: a simple yet effective language-independent layout transformer for structured document understanding. arXiv preprint arXiv:2202.13669 (2022)","DOI":"10.18653\/v1\/2022.acl-long.534"},{"key":"18_CR34","unstructured":"Weischedel, R., et al.: Ontonotes release 5.0 ldc2013t19. Linguistic Data Consortium, Philadelphia, PA 23 (2013)"},{"key":"18_CR35","doi-asserted-by":"publisher","unstructured":"Xu, Y., et al.: LayoutLMv2: multi-modal pre-training for visually-rich document understanding. In: Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), pp. 2579\u20132591. Association for Computational Linguistics, August 2021. https:\/\/doi.org\/10.18653\/v1\/2021.acl-long.201, https:\/\/aclanthology.org\/2021.acl-long.201","DOI":"10.18653\/v1\/2021.acl-long.201"},{"key":"18_CR36","doi-asserted-by":"publisher","unstructured":"Xu, Y., Li, M., Cui, L., Huang, S., Wei, F., Zhou, M.: Layoutlm: pre-training of text and layout for document image understanding. In: Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, KDD 2020, pp. 1192\u20131200. Association for Computing Machinery, New York, NY, USA (2020). https:\/\/doi.org\/10.1145\/3394486.3403172","DOI":"10.1145\/3394486.3403172"},{"key":"18_CR37","unstructured":"Xu, Y., et al.: Layoutxlm: multimodal pre-training for multilingual visually-rich document understanding. arXiv preprint arXiv:2104.08836 (2021)"},{"key":"18_CR38","unstructured":"Yu, W., Lu, N., Qi, X., Gong, P., Xiao, R.: Pick: processing key information extraction from documents using improved graph learning-convolutional networks (2020). https:\/\/arxiv.org\/abs\/2004.07464"}],"container-title":["Lecture Notes in Computer Science","Document Analysis and Recognition - ICDAR 2023"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-41682-8_18","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,18]],"date-time":"2023-08-18T07:19:49Z","timestamp":1692343189000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-41682-8_18"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031416811","9783031416828"],"references-count":38,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-41682-8_18","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"19 August 2023","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":"San Jos\u00e9, CA","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"USA","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2023","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"21 August 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26 August 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icdar2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/icdar2023.org\/","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":"316","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":"154","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":"49% - 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":"2.89","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":"1.50","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":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Number and type of other papers accepted : IJDAR track papers","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)"}}]}}