{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T15:30:38Z","timestamp":1759332638502,"version":"3.40.3"},"publisher-location":"Cham","reference-count":101,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783031136429"},{"type":"electronic","value":"9783031136436"}],"license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022]]},"DOI":"10.1007\/978-3-031-13643-6_8","type":"book-chapter","created":{"date-parts":[[2022,8,24]],"date-time":"2022-08-24T15:03:19Z","timestamp":1661353399000},"page":"105-117","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":10,"title":["Business Document Information Extraction: Towards Practical Benchmarks"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0197-7134","authenticated-orcid":false,"given":"Maty\u00e1\u0161","family":"Skalick\u00fd","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6687-1210","authenticated-orcid":false,"given":"\u0160t\u011bp\u00e1n","family":"\u0160imsa","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2606-4470","authenticated-orcid":false,"given":"Michal","family":"U\u0159i\u010d\u00e1\u0159","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6321-0131","authenticated-orcid":false,"given":"Milan","family":"\u0160ulc","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2022,8,25]]},"reference":[{"key":"8_CR1","doi-asserted-by":"crossref","unstructured":"Antonacopoulos, A., Bridson, D., Papadopoulos, C., Pletschacher, S.: A realistic dataset for performance evaluation of document layout analysis. In: Proceedings of ICDAR, pp. 296\u2013300. IEEE (2009)","DOI":"10.1109\/ICDAR.2009.271"},{"key":"8_CR2","doi-asserted-by":"crossref","unstructured":"Baek, Y., Lee, B., Han, D., Yun, S., Lee, H.: Character region awareness for text detection. In: Proceedings of the IEEE\/CVF CVPR, pp. 9365\u20139374 (2019)","DOI":"10.1109\/CVPR.2019.00959"},{"key":"8_CR3","doi-asserted-by":"publisher","unstructured":"Baviskar, D., Ahirrao, S., Kotecha, K.: Multi-layout invoice document dataset (MIDD): a dataset for named entity recognition. Data (2021). https:\/\/doi.org\/10.3390\/data6070078","DOI":"10.3390\/data6070078"},{"key":"8_CR4","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":"8_CR5","unstructured":"Berge, J.: The EDIFACT Standards. Blackwell Publishers, Inc. (1994)"},{"key":"8_CR6","unstructured":"Borchmann, \u0141., et al.: DUE: End-to-end document understanding benchmark. In: Proceedings of NeurIPS (2021)"},{"key":"8_CR7","unstructured":"Bosak, J., McGrath, T., Holman, G.K.: Universal business language v2. 0. Organization for the Advancement of Structured Information Standards (OASIS), Standard (2006)"},{"issue":"2","key":"8_CR8","doi-asserted-by":"publisher","first-page":"102","DOI":"10.1007\/s10032-002-0084-6","volume":"6","author":"F Cesarini","year":"2003","unstructured":"Cesarini, F., Francesconi, E., Gori, M., Soda, G.: Analysis and understanding of multi-class invoices. Doc. Anal. Recogn. 6(2), 102\u2013114 (2003)","journal-title":"Doc. Anal. Recogn."},{"key":"8_CR9","doi-asserted-by":"publisher","unstructured":"Chaudhry, R., Shekhar, S., Gupta, U., Maneriker, P., Bansal, P., Joshi, A.: LEAF-QA: locate, encode & attend for figure question answering. In: Proceedings of WACV, pp. 3501\u20133510. IEEE (2020). https:\/\/doi.org\/10.1109\/WACV45572.2020.9093269","DOI":"10.1109\/WACV45572.2020.9093269"},{"key":"8_CR10","doi-asserted-by":"crossref","unstructured":"Chen, L., et al.: WebSRC: a dataset for web-based structural reading comprehension. CoRR (2021)","DOI":"10.18653\/v1\/2021.emnlp-main.343"},{"key":"8_CR11","unstructured":"Chen, W., Chang, M., Schlinger, E., Wang, W.Y., Cohen, W.W.: Open question answering over tables and text. In: Proceedings of ICLR (2021)"},{"key":"8_CR12","unstructured":"Chen, W., et al.: TabFact: a large-scale dataset for table-based fact verification. In: Proceedings of ICLR (2020)"},{"key":"8_CR13","doi-asserted-by":"publisher","unstructured":"Chen, W., Zha, H., Chen, Z., Xiong, W., Wang, H., Wang, W.Y.: HybridQA: a dataset of multi-hop question answering over tabular and textual data. In: Cohn, T., He, Y., Liu, Y. (eds.) Findings of the Association for Computational Linguistics: EMNLP. Findings of ACL, vol. EMNLP 2020, pp. 1026\u20131036. Association for Computational Linguistics (2020). https:\/\/doi.org\/10.18653\/v1\/2020.findings-emnlp.91","DOI":"10.18653\/v1\/2020.findings-emnlp.91"},{"key":"8_CR14","unstructured":"Cho, M., Amplayo, R.K., Hwang, S., Park, J.: Adversarial TableQA: attention supervision for question answering on tables. In: Zhu, J., Takeuchi, I. (eds.) Proceedings of ACML. Proceedings of Machine Learning Research, vol. 95, pp. 391\u2013406 (2018)"},{"key":"8_CR15","doi-asserted-by":"crossref","unstructured":"Clausner, C., Antonacopoulos, A., Pletschacher, S.: ICDAR 2019 competition on recognition of documents with complex layouts-RDCL2019. In: Proceedings of ICDAR, pp. 1521\u20131526. IEEE (2019)","DOI":"10.1109\/ICDAR.2019.00245"},{"key":"8_CR16","doi-asserted-by":"publisher","first-page":"67","DOI":"10.1016\/j.ijinfomgt.2018.01.010","volume":"40","author":"M Cristani","year":"2018","unstructured":"Cristani, M., Bertolaso, A., Scannapieco, S., Tomazzoli, C.: Future paradigms of automated processing of business documents. Int. J. Inf. Manag. 40, 67\u201375 (2018)","journal-title":"Int. J. Inf. Manag."},{"key":"8_CR17","doi-asserted-by":"crossref","unstructured":"d\u2019Andecy, V.P., Hartmann, E., Rusinol, M.: Field extraction by hybrid incremental and a-priori structural templates. In: 2018 13th IAPR International Workshop on Document Analysis Systems (DAS), pp. 251\u2013256. IEEE (2018)","DOI":"10.1109\/DAS.2018.29"},{"key":"8_CR18","doi-asserted-by":"publisher","unstructured":"Deng, Y., Rosenberg, D.S., Mann, G.: Challenges in end-to-end neural scientific table recognition. In: Proceedings of ICDAR, pp. 894\u2013901. IEEE (2019). https:\/\/doi.org\/10.1109\/ICDAR.2019.00148","DOI":"10.1109\/ICDAR.2019.00148"},{"key":"8_CR19","unstructured":"Denk, T.I., Reisswig, C.: BERTgrid: contextualized embedding for 2D document representation and understanding. arXiv preprint arXiv:1909.04948 (2019)"},{"key":"8_CR20","doi-asserted-by":"crossref","unstructured":"Dhakal, P., Munikar, M., Dahal, B.: One-shot template matching for automatic document data capture. In: Proceedings of Artificial Intelligence for Transforming Business and Society (AITB), vol. 1, pp. 1\u20136. IEEE (2019)","DOI":"10.1109\/AITB48515.2019.8947440"},{"key":"8_CR21","unstructured":"Directive 2014\/55\/EU of the European parliament and of the council on electronic invoicing in public procurement, April 2014. https:\/\/eur-lex.europa.eu\/eli\/dir\/2014\/55\/oj"},{"key":"8_CR22","doi-asserted-by":"publisher","unstructured":"Fang, J., Tao, X., Tang, Z., Qiu, R., Liu, Y.: Dataset, ground-truth and performance metrics for table detection evaluation. In: Blumenstein, M., Pal, U., Uchida, S. (eds.) Proceedings of IAPR International Workshop on Document Analysis Systems, DAS, pp. 445\u2013449. IEEE (2012). https:\/\/doi.org\/10.1109\/DAS.2012.29","DOI":"10.1109\/DAS.2012.29"},{"key":"8_CR23","unstructured":"Ford, G., Thoma, G.R.: Ground truth data for document image analysis. In: Symposium on Document Image Understanding and Technology, pp. 199\u2013205. Citeseer (2003)"},{"key":"8_CR24","doi-asserted-by":"publisher","unstructured":"Gao, L., Yi, X., Jiang, Z., Hao, L., Tang, Z.: ICDAR2017 competition on page object detection. In: Proceedings of ICDAR, pp. 1417\u20131422 (2017). https:\/\/doi.org\/10.1109\/ICDAR.2017.231","DOI":"10.1109\/ICDAR.2017.231"},{"key":"8_CR25","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":"8_CR26","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":"8_CR27","doi-asserted-by":"crossref","unstructured":"Jaume, G., Ekenel, H.K., Thiran, J.P.: FUNSD: a dataset for form understanding in noisy scanned documents. In: ICDAR-OST (2019, accepted)","DOI":"10.1109\/ICDARW.2019.10029"},{"key":"8_CR28","doi-asserted-by":"crossref","unstructured":"Hamad, K.A., Mehmet, K.: A detailed analysis of optical character recognition technology. Int. J. Appl. Math. Electron. Comput. 1(Special Issue-1), 244\u2013249 (2016)","DOI":"10.18100\/ijamec.270374"},{"key":"8_CR29","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"404","DOI":"10.1007\/978-3-540-74141-1_28","volume-title":"Case-Based Reasoning Research and Development","author":"H Hamza","year":"2007","unstructured":"Hamza, H., Bela\u00efd, Y., Bela\u00efd, A.: Case-based reasoning for invoice analysis and recognition. In: Weber, R.O., Richter, M.M. (eds.) ICCBR 2007. LNCS (LNAI), vol. 4626, pp. 404\u2013418. Springer, Heidelberg (2007). https:\/\/doi.org\/10.1007\/978-3-540-74141-1_28"},{"key":"8_CR30","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":"8_CR31","doi-asserted-by":"publisher","first-page":"321","DOI":"10.1016\/j.patcog.2016.09.017","volume":"63","author":"S He","year":"2017","unstructured":"He, S., Schomaker, L.: Beyond OCR: multi-faceted understanding of handwritten document characteristics. Pattern Recogn. 63, 321\u2013333 (2017)","journal-title":"Pattern Recogn."},{"key":"8_CR32","unstructured":"Hole\u010dek, M.: Learning from similarity and information extraction from structured documents. Int. J. Doc. Anal. Recogn. (IJDAR) 1\u201317 (2021)"},{"key":"8_CR33","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":"8_CR34","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":"8_CR35","doi-asserted-by":"publisher","unstructured":"Huang, Z., et al.: ICDAR2019 competition on scanned receipt OCR and information extraction. In: Proceedings of ICDAR, pp. 1516\u20131520. IEEE (2019). https:\/\/doi.org\/10.1109\/ICDAR.2019.00244","DOI":"10.1109\/ICDAR.2019.00244"},{"key":"8_CR36","unstructured":"Islam, N., Islam, Z., Noor, N.: A survey on optical character recognition system. arXiv preprint arXiv:1710.05703 (2017)"},{"key":"8_CR37","doi-asserted-by":"publisher","first-page":"11","DOI":"10.1007\/978-1-4614-3223-4_2","volume-title":"Mining Text Data","author":"J Jiang","year":"2012","unstructured":"Jiang, J.: Information extraction from text. In: Aggarwal, C., Zhai, C. (eds.) Mining Text Data, pp. 11\u201341. Springer, Cham (2012). https:\/\/doi.org\/10.1007\/978-1-4614-3223-4_2"},{"key":"8_CR38","doi-asserted-by":"publisher","unstructured":"Jobin, K.V., Mondal, A., Jawahar, C.V.: DocFigure: a dataset for scientific document figure classification. In: 13th IAPR International Workshop on Graphics Recognition, GREC@ICDAR, pp. 74\u201379. IEEE (2019). https:\/\/doi.org\/10.1109\/ICDARW.2019.00018","DOI":"10.1109\/ICDARW.2019.00018"},{"key":"8_CR39","doi-asserted-by":"crossref","unstructured":"Kardas, M., et al.: AxCell: automatic extraction of results from machine learning papers. arXiv preprint arXiv:2004.14356 (2020)","DOI":"10.18653\/v1\/2020.emnlp-main.692"},{"key":"8_CR40","doi-asserted-by":"crossref","unstructured":"Katti, A.R., et al.: Chargrid: towards understanding 2D documents. arXiv preprint arXiv:1809.08799 (2018)","DOI":"10.18653\/v1\/D18-1476"},{"key":"8_CR41","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":"8_CR42","unstructured":"Kumar, A., et al.: Ask me anything: dynamic memory networks for natural language processing. In: Balcan, M., Weinberger, K.Q. (eds.) Proceedings of ICML, vol. 48, pp. 1378\u20131387. JMLR.org (2016)"},{"key":"8_CR43","doi-asserted-by":"publisher","unstructured":"Lample, G., Ballesteros, M., Subramanian, S., Kawakami, K., Dyer, C.: Neural architectures for named entity recognition. In: Knight, K., Nenkova, A., Rambow, O. (eds.) Proceedings of NAACL HLT, pp. 260\u2013270 (2016). https:\/\/doi.org\/10.18653\/v1\/n16-1030","DOI":"10.18653\/v1\/n16-1030"},{"key":"8_CR44","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"},{"issue":"20","key":"8_CR45","doi-asserted-by":"publisher","first-page":"29183","DOI":"10.1007\/s11042-018-6656-3","volume":"78","author":"J Li","year":"2019","unstructured":"Li, J., Wang, S., Wang, Y., Tang, Z.: Synthesizing data for text recognition with style transfer. Multimed. Tools Appl. 78(20), 29183\u201329196 (2019)","journal-title":"Multimed. Tools Appl."},{"key":"8_CR46","unstructured":"Li, M., Cui, L., Huang, S., Wei, F., Zhou, M., Li, Z.: TableBank: table benchmark for image-based table detection and recognition. In: Calzolari, N., et al. (eds.) Proceedings of The 12th Language Resources and Evaluation Conference, LREC. pp. 1918\u20131925 (2020)"},{"key":"8_CR47","unstructured":"Liu, W., Zhang, Y., Wan, B.: Unstructured document recognition on business invoice. Machine Learning, Stanford iTunes University, Stanford, CA, USA, Technical report (2016)"},{"key":"8_CR48","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":"8_CR49","doi-asserted-by":"crossref","unstructured":"Mathew, M., Bagal, V., Tito, R., Karatzas, D., Valveny, E., Jawahar, C.: InfographicVQA. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 1697\u20131706 (2022)","DOI":"10.1109\/WACV51458.2022.00264"},{"key":"8_CR50","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":"8_CR51","unstructured":"McCann, B., Keskar, N.S., Xiong, C., Socher, R.: The natural language decathlon: multitask learning as question answering. CoRR (2018)"},{"key":"8_CR52","unstructured":"Meadows, B., Seaburg, L.: Universal business language 1.0. Organization for the Advancement of Structured Information Standards (OASIS) (2004)"},{"issue":"4","key":"8_CR53","doi-asserted-by":"publisher","first-page":"335","DOI":"10.1007\/s10032-010-0137-1","volume":"14","author":"E Medvet","year":"2011","unstructured":"Medvet, E., Bartoli, A., Davanzo, G.: A probabilistic approach to printed document understanding. Int. J. Doc. Anal. Recogn. 14(4), 335\u2013347 (2011). https:\/\/doi.org\/10.1007\/s10032-010-0137-1","journal-title":"Int. J. Doc. Anal. Recogn."},{"key":"8_CR54","doi-asserted-by":"publisher","first-page":"142642","DOI":"10.1109\/ACCESS.2020.3012542","volume":"8","author":"J Memon","year":"2020","unstructured":"Memon, J., Sami, M., Khan, R.A., Uddin, M.: Handwritten optical character recognition (OCR): a comprehensive systematic literature review (SLR). IEEE Access 8, 142642\u2013142668 (2020)","journal-title":"IEEE Access"},{"key":"8_CR55","doi-asserted-by":"publisher","unstructured":"Methani, N., Ganguly, P., Khapra, M.M., Kumar, P.: PlotQA: reasoning over scientific plots. In: Proceedings of WACV, pp. 1516\u20131525 (2020). https:\/\/doi.org\/10.1109\/WACV45572.2020.9093523","DOI":"10.1109\/WACV45572.2020.9093523"},{"key":"8_CR56","doi-asserted-by":"publisher","unstructured":"Nadeau, D., Sekine, S.: A survey of named entity recognition and classification. Lingvistic\u00e6 Investigationes, pp. 3\u201326 (2007). https:\/\/doi.org\/10.1075\/li.30.1.03nad","DOI":"10.1075\/li.30.1.03nad"},{"key":"8_CR57","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":"8_CR58","doi-asserted-by":"crossref","unstructured":"Nayef, N., et al.: ICDAR 2019 robust reading challenge on multi-lingual scene text detection and recognition-RRC-MLT-2019. In: Proceedings of ICDAR, pp. 1582\u20131587. IEEE (2019)","DOI":"10.1109\/ICDAR.2019.00254"},{"key":"8_CR59","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":"8_CR60","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":"8_CR61","unstructured":"Park, S., el al.: Cord: a consolidated receipt dataset for post-OCR parsing. In: Workshop on Document Intelligence at NeurIPS 2019 (2019)"},{"key":"8_CR62","doi-asserted-by":"publisher","unstructured":"Prasad, D., Gadpal, A., Kapadni, K., Visave, M., Sultanpure, K.: CascadeTabNet: an approach for end to end table detection and structure recognition from image-based documents. In: Proceedings of CVPRw, pp. 2439\u20132447 (2020). https:\/\/doi.org\/10.1109\/CVPRW50498.2020.00294","DOI":"10.1109\/CVPRW50498.2020.00294"},{"key":"8_CR63","doi-asserted-by":"publisher","unstructured":"Qasim, S.R., Mahmood, H., Shafait, F.: Rethinking table recognition using graph neural networks. In: Proceedings of ICDAR, pp. 142\u2013147. IEEE (2019). https:\/\/doi.org\/10.1109\/ICDAR.2019.00031","DOI":"10.1109\/ICDAR.2019.00031"},{"key":"8_CR64","unstructured":"Raffel, C., et al.: Exploring the limits of transfer learning with a unified text-to-text transformer. arXiv preprint arXiv:1910.10683 (2019)"},{"key":"8_CR65","doi-asserted-by":"publisher","unstructured":"Rastogi, M., et al.: Information extraction from document images via FCA based template detection and knowledge graph rule induction. In: Proceedings of CVPRw, pp. 2377\u20132385 (2020). https:\/\/doi.org\/10.1109\/CVPRW50498.2020.00287","DOI":"10.1109\/CVPRW50498.2020.00287"},{"key":"8_CR66","doi-asserted-by":"crossref","unstructured":"Riba, P., Dutta, A., Goldmann, L., Forn\u00e9s, A., Ramos, O., Llad\u00f3s, J.: Table detection in invoice documents by graph neural networks. In: 2019 International Conference on Document Analysis and Recognition (ICDAR), pp. 122\u2013127. IEEE (2019)","DOI":"10.1109\/ICDAR.2019.00028"},{"key":"8_CR67","doi-asserted-by":"crossref","unstructured":"Rusinol, M., Benkhelfallah, T., Poulain dAndecy, V.: Field extraction from administrative documents by incremental structural templates. In: 2013 12th International Conference on Document Analysis and Recognition, pp. 1100\u20131104. IEEE (2013)","DOI":"10.1109\/ICDAR.2013.223"},{"key":"8_CR68","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: Proceedings of ICDAR, pp. 1162\u20131167 (2017). https:\/\/doi.org\/10.1109\/ICDAR.2017.192","DOI":"10.1109\/ICDAR.2017.192"},{"key":"8_CR69","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":"8_CR70","doi-asserted-by":"publisher","unstructured":"Shahab, A., Shafait, F., Kieninger, T., Dengel, A.: An open approach towards the benchmarking of table structure recognition systems. In: Doermann, D.S., Govindaraju, V., Lopresti, D.P., Natarajan, P. (eds.) The Ninth IAPR International Workshop on Document Analysis Systems, DAS, pp. 113\u2013120 (2010). https:\/\/doi.org\/10.1145\/1815330.1815345","DOI":"10.1145\/1815330.1815345"},{"key":"8_CR71","doi-asserted-by":"publisher","unstructured":"Siegel, N., Lourie, N., Power, R., Ammar, W.: Extracting scientific figures with distantly supervised neural networks. In: Chen, J., Gon\u00e7alves, M.A., Allen, J.M., Fox, E.A., Kan, M., Petras, V. (eds.) Proceedings of the 18th ACM\/IEEE on Joint Conference on Digital Libraries, JCDL, pp. 223\u2013232 (2018). https:\/\/doi.org\/10.1145\/3197026.3197040","DOI":"10.1145\/3197026.3197040"},{"key":"8_CR72","doi-asserted-by":"crossref","unstructured":"Smith, R.: An overview of the tesseract OCR engine. In: Ninth International Conference on Document Analysis and Recognition (ICDAR 2007), vol. 2, pp. 629\u2013633. IEEE (2007)","DOI":"10.1109\/ICDAR.2007.4376991"},{"key":"8_CR73","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":"8_CR74","doi-asserted-by":"crossref","unstructured":"Stockerl, M., Ringlstetter, C., Schubert, M., Ntoutsi, E., Kriegel, H.P.: Online template matching over a stream of digitized documents. In: Proceedings of the 27th International Conference on Scientific and Statistical Database Management, pp. 1\u201312 (2015)","DOI":"10.1145\/2791347.2791354"},{"key":"8_CR75","unstructured":"Stray, J., Svetlichnaya, S.: DeepForm: extract information from documents (2020). https:\/\/wandb.ai\/deepform\/political-ad-extraction, benchmark"},{"key":"8_CR76","unstructured":"Sun, H., Kuang, Z., Yue, X., Lin, C., Zhang, W.: Spatial dual-modality graph reasoning for key information extraction. arXiv preprint arXiv:2103.14470 (2021)"},{"key":"8_CR77","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":"8_CR78","doi-asserted-by":"crossref","unstructured":"Tensmeyer, C., Morariu, V.I., Price, B., Cohen, S., Martinez, T.: Deep splitting and merging for table structure decomposition. In: 2019 International Conference on Document Analysis and Recognition (ICDAR), pp. 114\u2013121. IEEE (2019)","DOI":"10.1109\/ICDAR.2019.00027"},{"key":"8_CR79","doi-asserted-by":"crossref","unstructured":"Wang, J., et al.: Towards robust visual information extraction in real world: new dataset and novel solution. In: Proceedings of the AAAI Conference on Artificial Intelligence (2021)","DOI":"10.1609\/aaai.v35i4.16378"},{"key":"8_CR80","unstructured":"Web: Annual reports. https:\/\/www.annualreports.com\/. Accessed 28 Apr 2022"},{"key":"8_CR81","unstructured":"Web: Charity Commission for England and Wales. https:\/\/apps.charitycommission.gov.uk\/showcharity\/registerofcharities\/RegisterHomePage.aspx. Accessed 22 Apr 2022"},{"key":"8_CR82","unstructured":"Web: EDGAR. https:\/\/www.sec.gov\/edgar.shtml. Accessed 22 Apr 2022"},{"key":"8_CR83","unstructured":"Web: Industry Documents Library. https:\/\/www.industrydocuments.ucsf.edu\/. Accessed 22 Apr 2022"},{"key":"8_CR84","unstructured":"Web: NIST Special Database 2. https:\/\/www.nist.gov\/srd\/nist-special-database-2. Accessed 25 Apr 2022"},{"key":"8_CR85","unstructured":"Web: Open Government Data (OGD) Platform India. https:\/\/visualize.data.gov.in\/. Accessed 22 Apr 2022"},{"key":"8_CR86","unstructured":"Web: Public Inspection Files. https:\/\/publicfiles.fcc.gov\/. Accessed 22 Apr 2022"},{"key":"8_CR87","unstructured":"Web: Scitsr. https:\/\/github.com\/Academic-Hammer\/SciTSR. Accessed 26 Apr 2022"},{"key":"8_CR88","unstructured":"Web: S &P 500 Companies with Financial Information. https:\/\/www.spglobal.com\/spdji\/en\/indices\/equity\/sp-500\/#data. Accessed 25 Apr 2022"},{"key":"8_CR89","unstructured":"Web: Statistics of Common Crawl Monthly Archives \u2013 MIME Types. https:\/\/commoncrawl.github.io\/cc-crawl-statistics\/plots\/mimetypes. Accessed 22 Apr 2022"},{"key":"8_CR90","unstructured":"Web: Tablebank. https:\/\/github.com\/doc-analysis\/TableBank. Accessed 26 Apr 2022"},{"key":"8_CR91","unstructured":"Web: World Bank Open Data. https:\/\/data.worldbank.org\/. Accessed 22 Apr 2022"},{"key":"8_CR92","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: Gupta, R., Liu, Y., Tang, J., Prakash, B.A. (eds.) Proceedings on KDD, pp. 1192\u20131200 (2020). https:\/\/doi.org\/10.1145\/3394486.3403172","DOI":"10.1145\/3394486.3403172"},{"key":"8_CR93","unstructured":"Xu, Y., et al.: LayoutXLM: multimodal pre-training for multilingual visually-rich document understanding. CoRR (2021)"},{"key":"8_CR94","doi-asserted-by":"crossref","unstructured":"Yi, J., Sundaresan, N.: A classifier for semi-structured documents. In: Proceedings of the Sixth ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 340\u2013344 (2000)","DOI":"10.1145\/347090.347164"},{"key":"8_CR95","doi-asserted-by":"crossref","unstructured":"Yu, D., et al.: Towards accurate scene text recognition with semantic reasoning networks. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 12113\u201312122 (2020)","DOI":"10.1109\/CVPR42600.2020.01213"},{"key":"8_CR96","doi-asserted-by":"publisher","unstructured":"Yu, W., Lu, N., Qi, X., Gong, P., Xiao, R.: PICK: processing key information extraction from documents using improved graph learning-convolutional networks. In: Proceedings of ICPR, pp. 4363\u20134370. IEEE (2020). https:\/\/doi.org\/10.1109\/ICPR48806.2021.9412927","DOI":"10.1109\/ICPR48806.2021.9412927"},{"key":"8_CR97","unstructured":"Zhao, X., Wu, Z., Wang, X.: CUTIE: learning to understand documents with convolutional universal text information extractor. CoRR abs\/1903.12363 (2019). http:\/\/arxiv.org\/abs\/1903.12363"},{"key":"8_CR98","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"},{"key":"8_CR99","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"564","DOI":"10.1007\/978-3-030-58589-1_34","volume-title":"Computer Vision \u2013 ECCV 2020","author":"X Zhong","year":"2020","unstructured":"Zhong, X., ShafieiBavani, E., Jimeno Yepes, A.: Image-based table recognition: data, model, and evaluation. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12366, pp. 564\u2013580. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58589-1_34"},{"key":"8_CR100","doi-asserted-by":"publisher","unstructured":"Zhong, X., Tang, J., Jimeno-Yepes, A.: PubLayNet: largest dataset ever for document layout analysis. In: Proceedings of ICDAR, pp. 1015\u20131022. IEEE, September 2019. https:\/\/doi.org\/10.1109\/ICDAR.2019.00166","DOI":"10.1109\/ICDAR.2019.00166"},{"key":"8_CR101","doi-asserted-by":"publisher","unstructured":"Zhu, F., et al.: TAT-QA: a question answering benchmark on a hybrid of tabular and textual content in finance. In: Zong, C., Xia, F., Li, W., Navigli, R. (eds.) Proceedings International Joint Conference on Natural Language Processing, pp. 3277\u20133287 (2021). https:\/\/doi.org\/10.18653\/v1\/2021.acl-long.254","DOI":"10.18653\/v1\/2021.acl-long.254"}],"container-title":["Lecture Notes in Computer Science","Experimental IR Meets Multilinguality, Multimodality, and Interaction"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-13643-6_8","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,12]],"date-time":"2024-03-12T16:33:21Z","timestamp":1710261201000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-13643-6_8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031136429","9783031136436"],"references-count":101,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-13643-6_8","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2022]]},"assertion":[{"value":"25 August 2022","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"CLEF","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference of the Cross-Language Evaluation Forum for European Languages","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Bologna","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"5 September 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 September 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"13","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"clef2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/clef2022.clef-initiative.eu\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Single-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":"14","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":"7","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":"3","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":"50% - 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":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"7 best of labs + 14 lab overviews","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)"}}]}}