{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,5,13]],"date-time":"2025-05-13T16:21:58Z","timestamp":1747153318159,"version":"3.40.5"},"publisher-location":"Cham","reference-count":21,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031415005"},{"type":"electronic","value":"9783031415012"}],"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\/978-3-031-41501-2_5","type":"book-chapter","created":{"date-parts":[[2023,8,14]],"date-time":"2023-08-14T20:04:21Z","timestamp":1692043461000},"page":"65-79","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["KAP: Pre-training Transformers for\u00a0Corporate Documents Understanding"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-2037-4364","authenticated-orcid":false,"given":"Ibrahim Souleiman","family":"Mahamoud","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0123-439X","authenticated-orcid":false,"given":"Micka\u00ebl","family":"Coustaty","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5499-6355","authenticated-orcid":false,"given":"Aur\u00e9lie","family":"Joseph","sequence":"additional","affiliation":[]},{"given":"Vincent Poulain","family":"d\u2019Andecy","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5666-475X","authenticated-orcid":false,"given":"Jean-Marc","family":"Ogier","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,8,15]]},"reference":[{"key":"5_CR1","doi-asserted-by":"crossref","unstructured":"Lannelongue, L., Grealey, J., Inouye, M.: Green Algorithms: Quantifying the carbon footprint of computation (2020)","DOI":"10.1002\/advs.202100707"},{"key":"5_CR2","doi-asserted-by":"publisher","unstructured":"Xu, Y., et al.: XFUND: a benchmark dataset for multilingual visually rich form understanding (2022). https:\/\/doi.org\/10.18653\/v1\/2022.findings-acl.253","DOI":"10.18653\/v1\/2022.findings-acl.253"},{"key":"5_CR3","unstructured":"Van Landeghem, J., et al.: Document understanding of everything"},{"key":"5_CR4","doi-asserted-by":"crossref","unstructured":"Sennrich, R., Haddow, B., Birch, A.: Neural machine translation of rare words with subword units (2016). arXiv:1508.0790","DOI":"10.18653\/v1\/P16-1162"},{"key":"5_CR5","unstructured":"Mahamoud, I.S., Coustaty, M., Joseph, A., d\u2019Andecy, V.P., Ogier, J.-M.: Corporate document for visual question answering (2022). https:\/\/arxiv.org\/pdf\/2305.01054.pdf"},{"key":"5_CR6","unstructured":"Mahamoud, I.S., Coustaty, M., Joseph, A., d\u2019Andecy, V.P., Ogier, J.-M.: To reproduce our experiments we put in this git account, the analyses and all the hyperparameters. https:\/\/gitlab.com\/contributions3\/kap.git"},{"key":"5_CR7","unstructured":"Dosovitskiy, A., et al.: An image is worth 16$$\\times $$16 words: transformers for image recognition at scale (2020)"},{"key":"5_CR8","unstructured":"Park, S., et al.: Neural machine translation of rare words with subword units (2016). arXiv:1508.0790"},{"key":"5_CR9","unstructured":"https:\/\/www.iso.org\/standard\/81090.html"},{"key":"5_CR10","unstructured":"Zhang, H., et al.: Machine Learning (stat.ML), Machine Learning (cs.LG), FOS: Computer and information sciences, FOS: Computer and information sciences"},{"key":"5_CR11","unstructured":"Lu, J., Yang, J., Batra, D., Parikh, D.: Computer Vision and Pattern Recognition (cs.CV), Computation and Language (cs.CL), FOS: Computer and information sciences, FOS: Computer and information sciences. https:\/\/arxiv.org\/abs\/1606.00061"},{"key":"5_CR12","unstructured":"Xu, Y., et al.: Neural machine translation of rare words with subword units (2016). arXiv:1508.0790"},{"key":"5_CR13","unstructured":"Xu, Y., et al.: LayoutLMv3: pre-training for document AI with unified text and image masking (2022)"},{"key":"5_CR14","doi-asserted-by":"crossref","unstructured":"Xu, Y., et al.: LayoutLMv2: multi-modal pre-training for visually-rich document understanding (2020)","DOI":"10.18653\/v1\/2021.acl-long.201"},{"key":"5_CR15","doi-asserted-by":"crossref","unstructured":"Mathew, M., Karatzas, D., Jawahar, C.V.: DocVQA: a dataset for VQA on document images (2021)","DOI":"10.1109\/WACV48630.2021.00225"},{"key":"5_CR16","unstructured":"Devlin, J., Chang, M.-W., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding (2018)"},{"key":"5_CR17","unstructured":"Liu, Y., et al.: RoBERTa: a robustly optimized BERT pretraining approach (2019)"},{"key":"5_CR18","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"532","DOI":"10.1007\/978-3-030-86549-8_34","volume-title":"Document Analysis and Recognition \u2013 ICDAR 2021","author":"\u0141 Garncarek","year":"2021","unstructured":"Garncarek, \u0141, et al.: LAMBERT: layout-aware language modeling for information extraction. In: Llad\u00f3s, J., Lopresti, D., Uchida, S. (eds.) ICDAR 2021. LNCS, vol. 12821, pp. 532\u2013547. Springer, Cham (2021). https:\/\/doi.org\/10.1007\/978-3-030-86549-8_34"},{"key":"5_CR19","doi-asserted-by":"crossref","unstructured":"Huang, Z., et al.: ICDAR2019 competition on scanned receipt OCR and information extraction (2019)","DOI":"10.1109\/ICDAR.2019.00244"},{"key":"5_CR20","doi-asserted-by":"crossref","unstructured":"Harley, A.W., Ufkes, A., Derpanis, K.G.: Evaluation of deep convolutional nets for document image classification and retrieval (2015)","DOI":"10.1109\/ICDAR.2015.7333910"},{"key":"5_CR21","doi-asserted-by":"crossref","unstructured":"Majumder, B.P., Potti, N., Tata, S., Wendt, J.B., Zhao, Q., Najork, M.: Representation learning for information extraction from form-like documents (2020)","DOI":"10.18653\/v1\/2020.acl-main.580"}],"container-title":["Lecture Notes in Computer Science","Document Analysis and Recognition \u2013 ICDAR 2023 Workshops"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-41501-2_5","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,14]],"date-time":"2023-08-14T20:07:00Z","timestamp":1692043620000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-41501-2_5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031415005","9783031415012"],"references-count":21,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-41501-2_5","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":"15 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)"}}]}}