{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,2]],"date-time":"2026-01-02T00:00:41Z","timestamp":1767312041398,"version":"3.48.0"},"publisher-location":"Cham","reference-count":27,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032093707","type":"print"},{"value":"9783032093714","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"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":[[2026]]},"DOI":"10.1007\/978-3-032-09371-4_6","type":"book-chapter","created":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T23:58:37Z","timestamp":1767311917000},"page":"85-100","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["SynFinTabs: A Dataset of\u00a0Synthetic Financial Tables for\u00a0Information and\u00a0Table Extraction"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3696-4253","authenticated-orcid":false,"given":"Ethan","family":"Bradley","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9035-2426","authenticated-orcid":false,"given":"Muhammad","family":"Roman","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7443-7876","authenticated-orcid":false,"given":"Karen","family":"Rafferty","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2128-8632","authenticated-orcid":false,"given":"Barry","family":"Devereux","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2026,1,2]]},"reference":[{"key":"6_CR1","doi-asserted-by":"publisher","unstructured":"Chen, Z., et al.: FinQA: a dataset of numerical reasoning over financial data. In: Moens, M.F., Huang, X., Specia, L., Yih, S.W.t. (eds.) Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pp. 3697\u20133711. Association for Computational Linguistics, Online and Punta Cana, Dominican Republic, November 2021. https:\/\/doi.org\/10.18653\/v1\/2021.emnlp-main.300, https:\/\/aclanthology.org\/2021.emnlp-main.300","DOI":"10.18653\/v1\/2021.emnlp-main.300"},{"key":"6_CR2","doi-asserted-by":"publisher","unstructured":"Chen, Z., Li, S., Smiley, C., Ma, Z., Shah, S., Wang, W.Y.: ConvFinQA: exploring the chain of numerical reasoning in conversational finance question answering. In: Goldberg, Y., Kozareva, Z., Zhang, Y. (eds.) Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pp. 6279\u20136292. Association for Computational Linguistics, Abu Dhabi, United Arab Emirates, December 2022. https:\/\/doi.org\/10.18653\/v1\/2022.emnlp-main.421, https:\/\/aclanthology.org\/2022.emnlp-main.421","DOI":"10.18653\/v1\/2022.emnlp-main.421"},{"key":"6_CR3","unstructured":"Chi, Z., Huang, H., Xu, H.D., Yu, H., Yin, W., Mao, X.L.: Complicated table structure recognition (2019)"},{"key":"6_CR4","unstructured":"Cui, L., Xu, Y., Lv, T., Wei, F.: Document AI: Benchmarks, models and applications (2021)"},{"key":"6_CR5","doi-asserted-by":"publisher","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: BERT: Pre-training of deep bidirectional transformers for language understanding. In: Burstein, J., Doran, C., Solorio, T. (eds.) 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), pp. 4171\u20134186. Association for Computational Linguistics, Minneapolis, Minnesota (Jun 2019). https:\/\/doi.org\/10.18653\/v1\/N19-1423, https:\/\/aclanthology.org\/N19-1423","DOI":"10.18653\/v1\/N19-1423"},{"key":"6_CR6","doi-asserted-by":"publisher","unstructured":"Eisenschlos, J., Gor, M., M\u00fcller, T., Cohen, W.: MATE: multi-view attention for table transformer efficiency. In: Moens, M.F., Huang, X., Specia, L., Yih, S.W.t. (eds.) Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pp. 7606\u20137619. Association for Computational Linguistics, Online and Punta Cana, Dominican Republic, November 2021. https:\/\/doi.org\/10.18653\/v1\/2021.emnlp-main.600, https:\/\/aclanthology.org\/2021.emnlp-main.600","DOI":"10.18653\/v1\/2021.emnlp-main.600"},{"key":"6_CR7","doi-asserted-by":"publisher","unstructured":"Gao, L., et al.: ICDAR 2019 competition on table detection and recognition (cTDaR). In: 2019 International Conference on Document Analysis and Recognition (ICDAR), pp. 1510\u20131515 (2019). https:\/\/doi.org\/10.1109\/ICDAR.2019.00243","DOI":"10.1109\/ICDAR.2019.00243"},{"key":"6_CR8","doi-asserted-by":"publisher","unstructured":"G\u00f6bel, M., Hassan, T., Oro, E., Orsi, G.: A methodology for evaluating algorithms for table understanding in PDF documents. In: Proceedings of the 2012 ACM Symposium on Document Engineering, DocEng \u201912, pp. 45\u201348. Association for Computing Machinery, New York (2012). https:\/\/doi.org\/10.1145\/2361354.2361365","DOI":"10.1145\/2361354.2361365"},{"key":"6_CR9","doi-asserted-by":"publisher","unstructured":"G\u00f6bel, M., Hassan, T., Oro, E., Orsi, G.: ICDAR 2013 table competition. In: 2013 12th International Conference on Document Analysis and Recognition, pp. 1449\u20131453 (2013). https:\/\/doi.org\/10.1109\/ICDAR.2013.292","DOI":"10.1109\/ICDAR.2013.292"},{"key":"6_CR10","doi-asserted-by":"publisher","unstructured":"Herzig, J., Nowak, P.K., M\u00fcller, T., Piccinno, F., Eisenschlos, J.: TaPas: Weakly supervised table parsing via pre-training. In: Jurafsky, D., Chai, J., Schluter, N., Tetreault, J. (eds.) Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pp. 4320\u20134333. Association for Computational Linguistics, Online, July 2020. https:\/\/doi.org\/10.18653\/v1\/2020.acl-main.398, https:\/\/aclanthology.org\/2020.acl-main.398","DOI":"10.18653\/v1\/2020.acl-main.398"},{"key":"6_CR11","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 (2022). https:\/\/doi.org\/10.1145\/3503161.3548112","DOI":"10.1145\/3503161.3548112"},{"key":"6_CR12","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":"6_CR13","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 Twelfth Language Resources and Evaluation Conference, pp. 1918\u20131925. European Language Resources Association, Marseille, France (May 2020), https:\/\/aclanthology.org\/2020.lrec-1.236"},{"key":"6_CR14","doi-asserted-by":"publisher","unstructured":"Li, M., Xu, Y., Cui, L., Huang, S., Wei, F., Li, Z., Zhou, M.: DocBank: A benchmark dataset for document layout analysis. In: Scott, D., Bel, N., Zong, C. (eds.) Proceedings of the 28th International Conference on Computational Linguistics, pp. 949\u2013960. International Committee on Computational Linguistics, Barcelona, Spain (Online), December 2020. https:\/\/doi.org\/10.18653\/v1\/2020.coling-main.82, https:\/\/aclanthology.org\/2020.coling-main.82","DOI":"10.18653\/v1\/2020.coling-main.82"},{"key":"6_CR15","unstructured":"OpenAI: GPT-4V(ision) system card (2023). https:\/\/cdn.openai.com\/papers\/GPTV_System_Card.pdf"},{"key":"6_CR16","doi-asserted-by":"publisher","unstructured":"Pasupat, P., Liang, P.: Compositional semantic parsing on semi-structured tables. In: Zong, C., Strube, M. (eds.) Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), pp. 1470\u20131480. Association for Computational Linguistics, Beijing, China, July 2015. https:\/\/doi.org\/10.3115\/v1\/P15-1142, https:\/\/aclanthology.org\/P15-1142","DOI":"10.3115\/v1\/P15-1142"},{"key":"6_CR17","unstructured":"PMC open access subset (2003). https:\/\/www.ncbi.nlm.nih.gov\/pmc\/tools\/openftlist\/"},{"key":"6_CR18","doi-asserted-by":"publisher","unstructured":"Qasim, S.R., Mahmood, H., Shafait, F.: Rethinking table recognition using graph neural networks. In: 2019 International Conference on Document Analysis and Recognition (ICDAR), pp. 142\u2013147 (2019). https:\/\/doi.org\/10.1109\/ICDAR.2019.00031","DOI":"10.1109\/ICDAR.2019.00031"},{"key":"6_CR19","doi-asserted-by":"crossref","unstructured":"Rajpurkar, P., Jia, R., Liang, P.: Know what you don\u2019t know: Unanswerable questions for SQuAD (2018)","DOI":"10.18653\/v1\/P18-2124"},{"key":"6_CR20","doi-asserted-by":"publisher","unstructured":"Rajpurkar, P., Zhang, J., Lopyrev, K., Liang, P.: SQuAD: 100,000+ questions for machine comprehension of text. In: Su, J., Duh, K., Carreras, X. (eds.) Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing. pp. 2383\u20132392. Association for Computational Linguistics, Austin, Texas, November 2016. https:\/\/doi.org\/10.18653\/v1\/D16-1264, https:\/\/aclanthology.org\/D16-1264","DOI":"10.18653\/v1\/D16-1264"},{"key":"6_CR21","doi-asserted-by":"publisher","unstructured":"Smock, B., Pesala, R., Abraham, R.: PubTables-1M: towards comprehensive table extraction from unstructured documents. In: 2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 4624\u20134632 (2022). https:\/\/doi.org\/10.1109\/CVPR52688.2022.00459","DOI":"10.1109\/CVPR52688.2022.00459"},{"key":"6_CR22","doi-asserted-by":"publisher","unstructured":"Xu, Y., et al.: LayoutLMv2: multi-modal pre-training for visually-rich document understanding. In: Zong, C., Xia, F., Li, W., Navigli, R. (eds.) 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, Online, 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":"6_CR23","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, pp. 1192\u20131200. KDD \u201920. Association for Computing Machinery, New York (2020). https:\/\/doi.org\/10.1145\/3394486.3403172","DOI":"10.1145\/3394486.3403172"},{"key":"6_CR24","doi-asserted-by":"publisher","unstructured":"Yang, X., Yumer, E., Asente, P., Kraley, M., Kifer, D., Giles, C.L.: Learning to extract semantic structure from documents using multimodal fully convolutional neural networks. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 4342\u20134351 (2017). https:\/\/doi.org\/10.1109\/CVPR.2017.462","DOI":"10.1109\/CVPR.2017.462"},{"key":"6_CR25","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: 2021 IEEE Winter Conference on Applications of Computer Vision (WACV), pp. 697\u2013706 (2021). https:\/\/doi.org\/10.1109\/WACV48630.2021.00074","DOI":"10.1109\/WACV48630.2021.00074"},{"key":"6_CR26","unstructured":"Zhong, V., Xiong, C., Socher, R.: Seq2SQL: Generating structured queries from natural language using reinforcement learning (2017)"},{"key":"6_CR27","doi-asserted-by":"publisher","unstructured":"Zhong, X., ShafieiBavani, E., Jimeno\u00a0Yepes, A.: Image-based table recognition: Data, model, and evaluation. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.M. (eds.) Computer Vision \u2013 ECCV 2020, pp. 564\u2013580. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58589-1_34","DOI":"10.1007\/978-3-030-58589-1_34"}],"container-title":["Lecture Notes in Computer Science","Document Analysis and Recognition \u2013 ICDAR 2025 Workshops"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-09371-4_6","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T23:58:39Z","timestamp":1767311919000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-09371-4_6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032093707","9783032093714"],"references-count":27,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-09371-4_6","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"2 January 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"The authors have no competing interests to declare that are relevant to the content of this article.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Disclosure of Interests"}},{"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":"Wuhan","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"16 September 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"21 September 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icdar2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/iapr.org\/icdar2025","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}