{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,29]],"date-time":"2025-11-29T08:00:46Z","timestamp":1764403246489,"version":"3.40.3"},"publisher-location":"Cham","reference-count":35,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031282409"},{"type":"electronic","value":"9783031282416"}],"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\/978-3-031-28241-6_69","type":"book-chapter","created":{"date-parts":[[2023,3,16]],"date-time":"2023-03-16T01:02:20Z","timestamp":1678928540000},"page":"600-608","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["DocILE 2023 Teaser: Document Information Localization and\u00a0Extraction"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6687-1210","authenticated-orcid":false,"given":"\u0160t\u011bp\u00e1n","family":"\u0160imsa","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6321-0131","authenticated-orcid":false,"given":"Milan","family":"\u0160ulc","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0197-7134","authenticated-orcid":false,"given":"Maty\u00e1\u0161","family":"Skalick\u00fd","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9373-529X","authenticated-orcid":false,"given":"Yash","family":"Patel","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8964-2135","authenticated-orcid":false,"given":"Ahmed","family":"Hamdi","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,3,16]]},"reference":[{"key":"69_CR1","doi-asserted-by":"crossref","unstructured":"Baek, Y., et al.: CLEVAL: character-level evaluation for text detection and recognition tasks. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops, pp. 564\u2013565 (2020)","DOI":"10.1109\/CVPRW50498.2020.00290"},{"key":"69_CR2","unstructured":"Bensch, O., Popa, M., Spille, C.: Key information extraction from documents: evaluation and generator. In: Abb\u00e8s, S.B., et al. (eds.) Proceedings of DeepOntoNLP and X-SENTIMENT. CEUR Workshop Proceedings, vol. 2918, pp. 47\u201353. CEUR-WS.org (2021)"},{"key":"69_CR3","unstructured":"Borchmann, \u0141., et al.: DUE: end-to-end document understanding benchmark. In: Proceeedings of NeurIPS (2021)"},{"key":"69_CR4","unstructured":"Denk, T.I., Reisswig, C.: Bertgrid: contextualized embedding for 2D document representation and understanding. arXiv preprint arXiv:1909.04948 (2019)"},{"key":"69_CR5","doi-asserted-by":"crossref","unstructured":"Dhakal, P., Munikar, M., Dahal, B.: One-shot template matching for automatic document data capture. In: Proceeedings of Artificial Intelligence for Transforming Business and Society (AITB), vol. 1, pp. 1\u20136. IEEE (2019)","DOI":"10.1109\/AITB48515.2019.8947440"},{"key":"69_CR6","doi-asserted-by":"crossref","unstructured":"Dosovitskiy, A., et al.: Flownet: learning optical flow with convolutional networks. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2758\u20132766 (2015)","DOI":"10.1109\/ICCV.2015.316"},{"key":"69_CR7","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":"69_CR8","doi-asserted-by":"publisher","unstructured":"G\u00f6bel, M.C., Hassan, T., Oro, E., Orsi, G.: ICDAR 2013 table competition. In: Proceedings of ICDAR, pp. 1449\u20131453. IEEE Computer Society (2013). https:\/\/doi.org\/10.1109\/ICDAR.2013.292","DOI":"10.1109\/ICDAR.2013.292"},{"key":"69_CR9","doi-asserted-by":"crossref","unstructured":"Jaume, G., Ekenel, H.K., Thiran, J.P.: Funsd: a dataset for form understanding in noisy scanned documents. In: Accepted to ICDAR-OST (2019)","DOI":"10.1109\/ICDARW.2019.10029"},{"key":"69_CR10","doi-asserted-by":"crossref","unstructured":"Gupta, A., Vedaldi, A., Zisserman, A.: Synthetic data for text localisation in natural images. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2315\u20132324 (2016)","DOI":"10.1109\/CVPR.2016.254"},{"key":"69_CR11","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"699","DOI":"10.1007\/978-3-030-86331-9_45","volume-title":"Document Analysis and Recognition \u2013 ICDAR 2021","author":"A Hamdi","year":"2021","unstructured":"Hamdi, A., Carel, E., Joseph, A., Coustaty, M., Doucet, A.: Information extraction from invoices. In: Llad\u00f3s, J., Lopresti, D., Uchida, S. (eds.) ICDAR 2021. LNCS, vol. 12822, pp. 699\u2013714. Springer, Cham (2021). https:\/\/doi.org\/10.1007\/978-3-030-86331-9_45"},{"key":"69_CR12","doi-asserted-by":"crossref","unstructured":"Harley, A.W., Ufkes, A., Derpanis, K.G.: Evaluation of deep convolutional nets for document image classification and retrieval. In: International Conference on Document Analysis and Recognition (ICDAR) (2015)","DOI":"10.1109\/ICDAR.2015.7333910"},{"key":"69_CR13","doi-asserted-by":"crossref","unstructured":"Hole\u010dek, M., Hoskovec, A., Baudi\u0161, P., Klinger, P.: Table understanding in structured documents. In: 2019 International Conference on Document Analysis and Recognition Workshops (ICDARW), vol. 5, pp. 158\u2013164. IEEE (2019)","DOI":"10.1109\/ICDARW.2019.40098"},{"key":"69_CR14","unstructured":"Holt, X., Chisholm, A.: Extracting structured data from invoices. In: Proceedings of the Australasian Language Technology Association Workshop 2018, pp. 53\u201359 (2018)"},{"key":"69_CR15","doi-asserted-by":"crossref","unstructured":"Katti, A.R., et al.: Chargrid: towards understanding 2D documents. In: Riloff, E., Chiang, D., Hockenmaier, J., Tsujii, J. (eds.) Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, Brussels, Belgium, 31 October\u20134 November 2018, pp. 4459\u20134469. Association for Computational Linguistics (2018). https:\/\/aclanthology.org\/D18-1476\/","DOI":"10.18653\/v1\/D18-1476"},{"key":"69_CR16","series-title":"Lecture Notes in Information Systems and Organisation","doi-asserted-by":"publisher","first-page":"5","DOI":"10.1007\/978-3-030-86797-3_1","volume-title":"Innovation Through Information Systems","author":"F Krieger","year":"2021","unstructured":"Krieger, F., Drews, P., Funk, B., Wobbe, T.: Information extraction from invoices: a graph neural network approach for datasets with high layout variety. In: Ahlemann, F., Sch\u00fctte, R., Stieglitz, S. (eds.) WI 2021. LNISO, vol. 47, pp. 5\u201320. Springer, Cham (2021). https:\/\/doi.org\/10.1007\/978-3-030-86797-3_1"},{"key":"69_CR17","doi-asserted-by":"crossref","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, pp. 665\u2013666 (2006)","DOI":"10.1145\/1148170.1148307"},{"key":"69_CR18","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"548","DOI":"10.1007\/978-3-030-86549-8_35","volume-title":"Document Analysis and Recognition \u2013 ICDAR 2021","author":"W Lin","year":"2021","unstructured":"Lin, W., Gao, Q., Sun, L., Zhong, Z., Hu, K., Ren, Q., Huo, Q.: ViBERTgrid: a jointly trained multi-modal 2D document representation for key information extraction from documents. In: Llad\u00f3s, J., Lopresti, D., Uchida, S. (eds.) ICDAR 2021. LNCS, vol. 12821, pp. 548\u2013563. Springer, Cham (2021). https:\/\/doi.org\/10.1007\/978-3-030-86549-8_35"},{"key":"69_CR19","unstructured":"Liu, W., Zhang, Y., Wan, B.: Unstructured document recognition on business invoice. Mach. Learn., Stanford iTunes Univ., Stanford, CA, USA, Technical Report (2016)"},{"key":"69_CR20","doi-asserted-by":"publisher","unstructured":"Majumder, B.P., Potti, N., Tata, S., Wendt, J.B., Zhao, Q., Najork, M.: Representation learning for information extraction from form-like documents. In: Jurafsky, D., Chai, J., Schluter, N., Tetreault, J.R. (eds.) Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, ACL, pp. 6495\u20136504 (2020). https:\/\/doi.org\/10.18653\/v1\/2020.acl-main.580","DOI":"10.18653\/v1\/2020.acl-main.580"},{"key":"69_CR21","doi-asserted-by":"publisher","unstructured":"Mathew, M., Karatzas, D., Jawahar, C.V.: Docvqa: a dataset for VQA on document images. In: Proceedings of WACV, pp. 2199\u20132208. IEEE (2021). https:\/\/doi.org\/10.1109\/WACV48630.2021.00225","DOI":"10.1109\/WACV48630.2021.00225"},{"key":"69_CR22","doi-asserted-by":"publisher","unstructured":"Nassar, A., Livathinos, N., Lysak, M., Staar, P.W.J.: Tableformer: table structure understanding with transformers. CoRR abs\/2203.01017 (2022). https:\/\/doi.org\/10.48550\/arXiv.2203.01017","DOI":"10.48550\/arXiv.2203.01017"},{"key":"69_CR23","doi-asserted-by":"crossref","unstructured":"Palm, R.B., Laws, F., Winther, O.: Attend, copy, parse end-to-end information extraction from documents. In: 2019 International Conference on Document Analysis and Recognition (ICDAR), pp. 329\u2013336. IEEE (2019)","DOI":"10.1109\/ICDAR.2019.00060"},{"key":"69_CR24","doi-asserted-by":"publisher","unstructured":"Palm, R.B., Winther, O., Laws, F.: Cloudscan - a configuration-free invoice analysis system using recurrent neural networks. In: Proceedings of ICDAR, pp. 406\u2013413. IEEE (2017). https:\/\/doi.org\/10.1109\/ICDAR.2017.74","DOI":"10.1109\/ICDAR.2017.74"},{"key":"69_CR25","doi-asserted-by":"crossref","unstructured":"Schuster, D., et al.: Intellix-end-user trained information extraction for document archiving. In: 2013 12th International Conference on Document Analysis and Recognition, pp. 101\u2013105. IEEE (2013)","DOI":"10.1109\/ICDAR.2013.28"},{"key":"69_CR26","doi-asserted-by":"publisher","unstructured":"Skalick\u00fd, M., \u0160imsa, \u0160., U\u0159i\u010d\u00e1\u0159, M., \u0160ulc, M.: Business document information extraction: towards practical benchmarks (2022). https:\/\/doi.org\/10.48550\/ARXIV.2206.11229, https:\/\/arxiv.org\/abs\/2206.11229","DOI":"10.48550\/ARXIV.2206.11229"},{"key":"69_CR27","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"564","DOI":"10.1007\/978-3-030-86549-8_36","volume-title":"Document Analysis and Recognition \u2013 ICDAR 2021","author":"T Stanis\u0142awek","year":"2021","unstructured":"Stanis\u0142awek, T., et al.: Kleister: key information extraction datasets involving long documents with complex layouts. In: Llad\u00f3s, J., Lopresti, D., Uchida, S. (eds.) ICDAR 2021. LNCS, vol. 12821, pp. 564\u2013579. Springer, Cham (2021). https:\/\/doi.org\/10.1007\/978-3-030-86549-8_36"},{"key":"69_CR28","unstructured":"Stray, J., Svetlichnaya, S.: Deepform: Extract information from documents (2020). https:\/\/wandb.ai\/deepform\/political-ad-extraction, benchmark"},{"key":"69_CR29","unstructured":"Sunder, V., Srinivasan, A., Vig, L., Shroff, G., Rahul, R.: One-shot information extraction from document images using neuro-deductive program synthesis. arXiv preprint arXiv:1906.02427 (2019)"},{"key":"69_CR30","unstructured":"Web: Industry Documents Library. https:\/\/www.industrydocuments.ucsf.edu\/. Accessed 20 Oct 2022"},{"key":"69_CR31","unstructured":"Web: Industry Documents Library API. https:\/\/www.industrydocuments.ucsf.edu\/research-tools\/api\/, Accessed 20 Oct 2022"},{"key":"69_CR32","unstructured":"Web: Public Inspection Files. https:\/\/publicfiles.fcc.gov\/. Accessed 20 Oct 2022"},{"key":"69_CR33","unstructured":"Xu, Y., et al.: LayoutXLM: multimodal pre-training for multilingual visually-rich document understanding. CoRR (2021)"},{"key":"69_CR34","unstructured":"Zhao, X., Wu, Z., Wang, X.: CUTIE: learning to understand documents with convolutional universal text information extractor. CoRR abs\/1903.12363 (2019). https:\/\/arxiv.org\/abs\/1903.12363"},{"key":"69_CR35","doi-asserted-by":"publisher","unstructured":"Zheng, X., Burdick, D., Popa, L., Zhong, X., Wang, N.X.R.: Global table extractor (GTE): a framework for joint table identification and cell structure recognition using visual context. In: Proceedings of WACV, pp. 697\u2013706. IEEE (2021). https:\/\/doi.org\/10.1109\/WACV48630.2021.00074","DOI":"10.1109\/WACV48630.2021.00074"}],"container-title":["Lecture Notes in Computer Science","Advances in Information Retrieval"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-28241-6_69","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,5]],"date-time":"2024-03-05T13:10:39Z","timestamp":1709644239000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-28241-6_69"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031282409","9783031282416"],"references-count":35,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-28241-6_69","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":"16 March 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECIR","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Information Retrieval","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Dublin","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Ireland","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":"2 April 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"6 April 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"45","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ecir2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/ecir2023.org\/index.html?v=1.0","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":"489","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":"77","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":"83","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":"16% - 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":"3","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":"3","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)"}}]}}