{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,3]],"date-time":"2026-07-03T18:18:49Z","timestamp":1783102729969,"version":"3.54.6"},"publisher-location":"Singapore","reference-count":18,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819699209","type":"print"},{"value":"9789819699216","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"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":[[2025]]},"DOI":"10.1007\/978-981-96-9921-6_34","type":"book-chapter","created":{"date-parts":[[2025,7,25]],"date-time":"2025-07-25T06:15:39Z","timestamp":1753424139000},"page":"419-431","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Advanced Font-Aware Document Hierarchy Reconstruction for Enhanced Structured Parsing"],"prefix":"10.1007","author":[{"given":"Xinpan","family":"Yuan","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Gan","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Liujie","family":"Hua","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guihu","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shaomin","family":"Xie","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,7,26]]},"reference":[{"key":"34_CR1","doi-asserted-by":"crossref","unstructured":"Ling, L., ChihHsuan, W., PoTing, L., et al.: AIONER: all-in-one scheme-based biomedical named entity recognition using deep learning. Bioinformatics (Oxford, England) 39(5) (2023)","DOI":"10.1093\/bioinformatics\/btad310"},{"key":"34_CR2","doi-asserted-by":"crossref","unstructured":"Sciannameo, V., et al.: Information extraction from medical case reports using open-AI instruct GPT. Comput. Methods Programs Biomed. 255, 108326 (2024)","DOI":"10.1016\/j.cmpb.2024.108326"},{"key":"34_CR3","doi-asserted-by":"crossref","unstructured":"Da, C., Luo, C., Zheng, Q., et al. Vision grid transformer for document layout analysis. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 19462\u201319472 (2023)","DOI":"10.1109\/ICCV51070.2023.01783"},{"key":"34_CR4","doi-asserted-by":"crossref","unstructured":"He, J., Wang, L., Hu, Y., et al.: ICL-D3IE: in-context learning with diverse demonstrations updating for document information extraction. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 19485\u201319494 (2023)","DOI":"10.1109\/ICCV51070.2023.01785"},{"key":"34_CR5","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Zhang, Z., Lai, W., et al.: to-tree: parsing pdf text blocks into a tree. In: Findings of the Association for Computational Linguistics: EMNLP 2024, pp. 10704\u201310714 (2024)","DOI":"10.18653\/v1\/2024.findings-emnlp.628"},{"key":"34_CR6","doi-asserted-by":"crossref","unstructured":"Chen, Z., Zhang, P., Xu, M., et al.: Locating GPT: a, multi-modal document retrieval method based on retrieval-augmented generation. In: 2024 IEEE 9th International Conference on Data Science in Cyberspace (DSC), pp. 232\u2013239. IEEE (2024)","DOI":"10.1109\/DSC63484.2024.00038"},{"key":"34_CR7","doi-asserted-by":"crossref","unstructured":"Long, S., Qin, S., Fujii, Y., et al.: Hierarchical text spotter for joint text spotting and layout analysis. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 903\u2013913 (2024)","DOI":"10.1109\/WACV57701.2024.00095"},{"issue":"1","key":"34_CR8","doi-asserted-by":"publisher","first-page":"1418","DOI":"10.1038\/s41467-024-45563-x","volume":"15","author":"J Dagdelen","year":"2024","unstructured":"Dagdelen, J., Dunn, A., Lee, S., et al.: Structured information extraction from scientific text with large language models. Nat. Commun. 15(1), 1418 (2024)","journal-title":"Nat. Commun."},{"key":"34_CR9","doi-asserted-by":"crossref","unstructured":"Hu, K., Wu, Z., Zhong, Z., et al.: A question-answering approach to key value pair extraction from form-like document images. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 37, no. 11, pp. 12899\u201312906 (2023)","DOI":"10.1609\/aaai.v37i11.26516"},{"key":"34_CR10","doi-asserted-by":"crossref","unstructured":"Zhu, X., Guo, X., Cao, S., et al.: Structu GraphRAG: structured document-informed knowledge graphs for retrieval-augmented generation. In: Proceedings of the AAAI Symposium Series, vol. 4 no. 1, pp. 242\u2013251 (2024)","DOI":"10.1609\/aaaiss.v4i1.31798"},{"key":"34_CR11","doi-asserted-by":"crossref","unstructured":"Liang, Y, Cao, H.: Large language model-driven semi-automated construction of named entity datasets in specific knowledge domain. In: 2024 9th International Symposium on Computer and Information Processing Technology (ISCIPT), pp. 312\u2013318. IEEE (2024)","DOI":"10.1109\/ISCIPT61983.2024.10673354"},{"key":"34_CR12","doi-asserted-by":"crossref","unstructured":"Malashin, I., et al.: Image text extraction and natural language processing of unstructured data from medical reports. Mach. Learn. Knowl. Extr. 6(2), 1361\u20131377 (2024)","DOI":"10.3390\/make6020064"},{"key":"34_CR13","doi-asserted-by":"crossref","unstructured":"Arachchi, N.H., Dayarathne, R.N., Aluthdeniya, N.D., et al.: Layout aware research paper parsing and draft research paper layout-error detection using NLP and rule-based techniques. In: 2024 9th International Conference on Information Technology Research (ICITR), pp. 1\u20136. IEEE (2024)","DOI":"10.1109\/ICITR64794.2024.10857771"},{"key":"34_CR14","doi-asserted-by":"crossref","unstructured":"Bocharova, M.Y., Malakhov, E.V.: CapStyleBERT: incorporating capitalization and style in-formation into BERT for enhanced resumes parsing. In: Proceedings of the 2024 13th International Conference on Software and Computer Applications, p. 1 (2024)","DOI":"10.1145\/3651781.3651820"},{"key":"34_CR15","doi-asserted-by":"crossref","unstructured":"Meuschke, N., Jagdale, A., Spinde, T., et al.: A benchmark of PDF information extraction tools using a multi-task and multi-domain evaluation framework for academic documents. In: International Conference on Information. Cham: Springer Nature Switzerland, pp. 383\u2013405 (2023)","DOI":"10.1007\/978-3-031-28032-0_31"},{"key":"34_CR16","doi-asserted-by":"crossref","unstructured":"Attouche, L., et al.: Validation of modern JSON schema: formalization and complexity. In: Proceedings of the ACM on Programming Languages 8. POPL, pp. 1451\u20131481 (2024)","DOI":"10.1145\/3632891"},{"key":"34_CR17","doi-asserted-by":"crossref","unstructured":"El Bahi, H.: Handwritten text recognition and information extraction from ancient manuscripts using deep convolutional and recurrent neural network. Soft Comput. 28(20), 12249\u201312268 (2024)","DOI":"10.1007\/s00500-024-09930-6"},{"key":"34_CR18","doi-asserted-by":"crossref","unstructured":"Lo, K., Shen, Z., Newman, B., et al.: PaperMage: aunified toolkit for processing, representing, and manipulating visually rich scientific documents. In: Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing: System Demonstrations, pp. 495\u2013507 (2023)","DOI":"10.18653\/v1\/2023.emnlp-demo.45"}],"container-title":["Lecture Notes in Computer Science","Advanced Intelligent Computing Technology and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-96-9921-6_34","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,3]],"date-time":"2026-07-03T17:43:40Z","timestamp":1783100620000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-96-9921-6_34"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9789819699209","9789819699216"],"references-count":18,"URL":"https:\/\/doi.org\/10.1007\/978-981-96-9921-6_34","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]},"assertion":[{"value":"26 July 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICIC","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Intelligent Computing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Ningbo","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":"26 July 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 July 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"21","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icic2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.ic-icc.cn\/icg\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}