{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,24]],"date-time":"2026-02-24T16:17:52Z","timestamp":1771949872527,"version":"3.50.1"},"publisher-location":"Cham","reference-count":23,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031724367","type":"print"},{"value":"9783031724374","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"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":[[2024]]},"DOI":"10.1007\/978-3-031-72437-4_1","type":"book-chapter","created":{"date-parts":[[2024,9,25]],"date-time":"2024-09-25T20:41:19Z","timestamp":1727296879000},"page":"3-19","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Learning Reading Order via\u00a0Document Layout with\u00a0Layout2Pos"],"prefix":"10.1007","author":[{"given":"Laura","family":"Nguyen","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Benjamin","family":"Piwowarski","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Julio","family":"Laborde","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gilles","family":"Moyse","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,9,26]]},"reference":[{"key":"1_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. arXiv preprint arXiv:2106.11539 (2021)","DOI":"10.1109\/ICCV48922.2021.00103"},{"key":"1_CR2","doi-asserted-by":"crossref","unstructured":"Gu, Z., et al.: Xylayoutlm: towards layout-aware multimodal networks for visually-rich document understanding. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4583\u20134592 (2022)","DOI":"10.1109\/CVPR52688.2022.00454"},{"key":"1_CR3","doi-asserted-by":"crossref","unstructured":"Ha, J., Haralick, R.M., Phillips, I.T.: Recursive XY cut using bounding boxes of connected components. In: Proceedings of 3rd International Conference on Document Analysis and Recognition, vol.\u00a02, pp. 952\u2013955, IEEE (1995)","DOI":"10.1109\/ICDAR.1995.602059"},{"key":"1_CR4","doi-asserted-by":"crossref","unstructured":"Huang, Z., et al.: ICDAR2019 competition on scanned receipt OCR and information extraction. In: 2019 International Conference on Document Analysis and Recognition (ICDAR), pp. 1516\u20131520. IEEE (2019)","DOI":"10.1109\/ICDAR.2019.00244"},{"key":"1_CR5","doi-asserted-by":"crossref","unstructured":"Jaume, G., Ekenel, H.K., 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.\u00a02, pp. 1\u20136. IEEE (2019)","DOI":"10.1109\/ICDARW.2019.10029"},{"key":"1_CR6","unstructured":"Kay, A.: Tesseract: an open-source optical character recognition engine. Linux J. 2007(159), 2 (2007). ISSN 1075-3583"},{"key":"1_CR7","series-title":"LNCS","doi-asserted-by":"publisher","first-page":"498","DOI":"10.1007\/978-3-031-19815-1_29","volume-title":"ECCV 2022","author":"G Kim","year":"2022","unstructured":"Kim, G., et al.: OCR-free document understanding transformer. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13688, pp. 498\u2013517. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-19815-1_29"},{"key":"1_CR8","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":"1_CR9","doi-asserted-by":"crossref","unstructured":"Lewis, M., et al.: Bart: denoising sequence-to-sequence pre-training for natural language generation, translation, and comprehension. arXiv preprint arXiv:1910.13461 (2019)","DOI":"10.18653\/v1\/2020.acl-main.703"},{"key":"1_CR10","unstructured":"Mindee: doctr: Document text recognition (2021). https:\/\/github.com\/mindee\/doctr"},{"key":"1_CR11","unstructured":"Park, S., et al.: Cord: a consolidated receipt dataset for post-OCR parsing. In: Workshop on Document Intelligence at NeurIPS 2019 (2019)"},{"key":"1_CR12","doi-asserted-by":"crossref","unstructured":"Peng, Q., et\u00a0al.: Ernie-layout: layout knowledge enhanced pre-training for visually-rich document understanding. arXiv preprint arXiv:2210.06155 (2022)","DOI":"10.18653\/v1\/2022.findings-emnlp.274"},{"key":"1_CR13","doi-asserted-by":"crossref","unstructured":"Powalski, R., Borchmann, \u0141., Jurkiewicz, D., Dwojak, T., Pietruszka, M., Pa\u0142ka, G.: Going full-tilt boogie on document understanding with text-image-layout transformer. arXiv preprint arXiv:2102.09550 (2021)","DOI":"10.1007\/978-3-030-86331-9_47"},{"issue":"1","key":"1_CR14","first-page":"5485","volume":"21","author":"C Raffel","year":"2020","unstructured":"Raffel, C., et al.: Exploring the limits of transfer learning with a unified text-to-text transformer. J. Mach. Learn. Res. 21(1), 5485\u20135551 (2020)","journal-title":"J. Mach. Learn. Res."},{"key":"1_CR15","doi-asserted-by":"publisher","first-page":"157","DOI":"10.1007\/978-94-017-2390-9_10","volume-title":"Natural Language Processing Using Very Large Corpora","author":"LA Ramshaw","year":"1999","unstructured":"Ramshaw, L.A., Marcus, M.P.: Text chunking using transformation-based learning. In: Armstrong, S., Church, K., Isabelle, P., Manzi, S., Tzoukermann, E., Yarowsky, D. (eds.) Natural Language Processing Using Very Large Corpora, pp. 157\u2013176. Springer, Dordrecht (1999). https:\/\/doi.org\/10.1007\/978-94-017-2390-9_10"},{"key":"1_CR16","doi-asserted-by":"crossref","unstructured":"Sage, C., Aussem, A., Eglin, V., Elghazel, H., Espinas, J.: End-to-end extraction of structured information from business documents with pointer-generator networks. In: Proceedings of the Fourth Workshop on Structured Prediction for NLP, pp. 43\u201352 (2020)","DOI":"10.18653\/v1\/2020.spnlp-1.6"},{"key":"1_CR17","doi-asserted-by":"crossref","unstructured":"See, A., Liu, P.J., Manning, C.D.: Get to the point: summarization with pointer-generator networks. arXiv preprint arXiv:1704.04368 (2017)","DOI":"10.18653\/v1\/P17-1099"},{"key":"1_CR18","unstructured":"Townsend, B., Ito-Fisher, E., Zhang, L., May, M.: Doc2dict: information extraction as text generation. arXiv preprint arXiv:2105.07510 (2021)"},{"key":"1_CR19","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems, vol. 30 (2017)"},{"key":"1_CR20","doi-asserted-by":"crossref","unstructured":"Wang, Z., Xu, Y., Cui, L., Shang, J., Wei, F.: Layoutreader: pre-training of text and layout for reading order detection (2021)","DOI":"10.18653\/v1\/2021.emnlp-main.389"},{"key":"1_CR21","doi-asserted-by":"crossref","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 (2020)","DOI":"10.1145\/3394486.3403172"},{"key":"1_CR22","doi-asserted-by":"crossref","unstructured":"Xu, Y., et al.: Layoutlmv2: multi-modal pre-training for visually-rich document understanding. arXiv preprint arXiv:2012.14740 (2020)","DOI":"10.18653\/v1\/2021.acl-long.201"},{"key":"1_CR23","doi-asserted-by":"crossref","unstructured":"Zhang, C., et al.: Reading order matters: information extraction from visually-rich documents by token path prediction. arXiv preprint arXiv:2310.11016 (2023)","DOI":"10.18653\/v1\/2023.emnlp-main.846"}],"container-title":["Lecture Notes in Computer Science","Linking Theory and Practice of Digital Libraries"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-72437-4_1","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,15]],"date-time":"2024-11-15T05:02:12Z","timestamp":1731646932000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72437-4_1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9783031724367","9783031724374"],"references-count":23,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72437-4_1","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]},"assertion":[{"value":"26 September 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"TPDL","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Theory and Practice of Digital Libraries","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Ljubljana","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Slovenia","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"24 September 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27 September 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"28","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"tpdl2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/tpdl2024.nuk.si\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}