{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,7]],"date-time":"2025-06-07T10:44:31Z","timestamp":1749293071147,"version":"3.40.3"},"publisher-location":"Cham","reference-count":26,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031705328"},{"type":"electronic","value":"9783031705335"}],"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\/978-3-031-70533-5_14","type":"book-chapter","created":{"date-parts":[[2024,9,7]],"date-time":"2024-09-07T05:02:25Z","timestamp":1725685345000},"page":"227-243","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["GraphMLLM: A Graph-Based Multi-level Layout Language-Independent Model for\u00a0Document Understanding"],"prefix":"10.1007","author":[{"given":"He-Sen","family":"Dai","sequence":"first","affiliation":[]},{"given":"Xiao-Hui","family":"Li","sequence":"additional","affiliation":[]},{"given":"Fei","family":"Yin","sequence":"additional","affiliation":[]},{"given":"Xudong","family":"Yan","sequence":"additional","affiliation":[]},{"given":"Shuqi","family":"Mei","sequence":"additional","affiliation":[]},{"given":"Cheng-Lin","family":"Liu","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,9,8]]},"reference":[{"key":"14_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. In: International Conference on Computer Vision, pp. 973\u2013983 (2021)","DOI":"10.1109\/ICCV48922.2021.00103"},{"key":"14_CR2","unstructured":"Bao, H., Dong, L., Piao, S., Wei, F.: Beit: bert pre-training of image transformers. In: International Conference on Learning Representations (2021)"},{"key":"14_CR3","doi-asserted-by":"crossref","unstructured":"Chi, Z., et al.: InfoXLM: an information-theoretic framework for cross-lingual language model pre-training. In: 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pp. 3576\u20133588 (2021)","DOI":"10.18653\/v1\/2021.naacl-main.280"},{"key":"14_CR4","unstructured":"Devlin, J., Chang, M., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. In: 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pp. 4171\u20134186 (2019)"},{"key":"14_CR5","doi-asserted-by":"crossref","unstructured":"Gu, Z., et al.: Xylayoutlm: towards layout-aware multimodal networks for visually-rich document understanding. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4583\u20134592 (2022)","DOI":"10.1109\/CVPR52688.2022.00454"},{"key":"14_CR6","unstructured":"He, P., Liu, X., Gao, J., Chen, W.: Deberta: decoding-enhanced Bert with disentangled attention. In: The 9th International Conference on Learning Representations (2021)"},{"key":"14_CR7","doi-asserted-by":"crossref","unstructured":"Hong, T., Kim, D., Ji, M., Hwang, W., Nam, D., Park, S.: BROS: a pre-trained language model focusing on text and layout for better key information extraction from documents. In: The 36th AAAI Conference on Artificial Intelligence, pp. 10767\u201310775 (2022)","DOI":"10.1609\/aaai.v36i10.21322"},{"key":"14_CR8","doi-asserted-by":"crossref","unstructured":"Huang, Y., Lv, T., Cui, L., Lu, Y., Wei, F.: Layoutlmv3: pre-training for document AI with unified text and image masking. In: The 30th ACM International Conference on Multimedia, pp. 4083\u20134091 (2022)","DOI":"10.1145\/3503161.3548112"},{"key":"14_CR9","doi-asserted-by":"crossref","unstructured":"Jaume, G., Ekenel, H.K., Thiran, J.: FUNSD: a dataset for form understanding in noisy scanned documents. In: The 2nd International Workshop on Open Services and Tools for Document Analysis, pp.\u00a01\u20136 (2019)","DOI":"10.1109\/ICDARW.2019.10029"},{"key":"14_CR10","doi-asserted-by":"crossref","unstructured":"Lewis, D.D., Agam, G., Argamon, S., Frieder, O., Grossman, D.A., Heard, J.: Building a test collection for complex document information processing. In: The 29th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, pp. 665\u2013666 (2006)","DOI":"10.1145\/1148170.1148307"},{"key":"14_CR11","doi-asserted-by":"crossref","unstructured":"Li, C., et al.: StructuralLM: structural pre-training for form understanding. In: The 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing, vol. 1: Long Papers, pp. 6309\u20136318 (2021)","DOI":"10.18653\/v1\/2021.acl-long.493"},{"key":"14_CR12","doi-asserted-by":"crossref","unstructured":"Li, J., Xu, Y., Lv, T., Cui, L., Zhang, C., Wei, F.: Dit: self-supervised pre-training for document image transformer. In: The 30th ACM International Conference on Multimedia, pp. 3530\u20133539 (2022)","DOI":"10.1145\/3503161.3547911"},{"key":"14_CR13","doi-asserted-by":"crossref","unstructured":"Li, P., et al.: Selfdoc: self-supervised document representation learning. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5652\u20135660 (2021)","DOI":"10.1109\/CVPR46437.2021.00560"},{"key":"14_CR14","doi-asserted-by":"crossref","unstructured":"Li, Y., et al.: Structext: structured text understanding with multi-modal transformers. In: The 21st ACM Multimedia Conference on Multimedia, pp. 1912\u20131920 (2021)","DOI":"10.1145\/3474085.3475345"},{"key":"14_CR15","unstructured":"Liu, Y., et al.: Roberta: a robustly optimized Bert pretraining approach. arXiv preprint arXiv:1907.11692 (2019)"},{"key":"14_CR16","unstructured":"Park, S., et al.: Cord: a consolidated receipt dataset for post-ocr parsing. In: Workshop on Document Intelligence at NeurIPS 2019 (2019)"},{"key":"14_CR17","doi-asserted-by":"crossref","unstructured":"Peng, Q., et al.: ERNIE-layout: layout knowledge enhanced pre-training for visually-rich document understanding. In: Findings of the Association for Computational Linguistics: EMNLP 2022, pp. 3744\u20133756 (2022)","DOI":"10.18653\/v1\/2022.findings-emnlp.274"},{"key":"14_CR18","unstructured":"Vaswani, A., et al.: Attention is all you need. Adv. Neural Inf. Process. Syst. 30, 5998\u20136008 (2017)"},{"key":"14_CR19","doi-asserted-by":"crossref","unstructured":"Wang, J., Jin, L., Ding, K.: LiLT: a simple yet effective language-independent layout transformer for structured document understanding. In: The 60th Annual Meeting of the Association for Computational Linguistics, vol. 1: Long Papers, pp. 7747\u20137757 (2022)","DOI":"10.18653\/v1\/2022.acl-long.534"},{"key":"14_CR20","doi-asserted-by":"crossref","unstructured":"Wang, J., et al.: Towards robust visual information extraction in real world: new dataset and novel solution. In: The AAAI Conference on Artificial Intelligence, pp. 2738\u20132745 (2021)","DOI":"10.1609\/aaai.v35i4.16378"},{"key":"14_CR21","doi-asserted-by":"crossref","unstructured":"Wang, W., et\u00a0al.: Ernie-mmlayout: multi-grained multimodal transformer for document understanding. arXiv preprint arXiv:2209.08569 (2022)","DOI":"10.1145\/3503161.3548406"},{"key":"14_CR22","doi-asserted-by":"crossref","unstructured":"Xu, Y., et al.: LayoutLMv2: multi-modal pre-training for visually-rich document understanding. In: The 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing, vol. 1: Long Papers, pp. 2579\u20132591 (2021)","DOI":"10.18653\/v1\/2021.acl-long.201"},{"key":"14_CR23","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: The 26th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, pp. 1192\u20131200 (2020)","DOI":"10.1145\/3394486.3403172"},{"key":"14_CR24","unstructured":"Xu, Y., et al.: Layoutxlm: multimodal pre-training for multilingual visually-rich document understanding. arXiv preprint arXiv:2104.08836 (2021)"},{"key":"14_CR25","doi-asserted-by":"crossref","unstructured":"Zhai, M., et al.: Fast-structext: an efficient hourglass transformer with modality-guided dynamic token merge for document understanding. arXiv preprint arXiv:2305.11392 (2023)","DOI":"10.24963\/ijcai.2023\/585"},{"key":"14_CR26","doi-asserted-by":"publisher","first-page":"6743","DOI":"10.1109\/TMM.2022.3214102","volume":"25","author":"Z Zhang","year":"2023","unstructured":"Zhang, Z., Ma, J., Du, J., Wang, L., Zhang, J.: Multimodal pre-training based on graph attention network for document understanding. IEEE Trans. Multimedia 25, 6743\u20136755 (2023)","journal-title":"IEEE Trans. Multimedia"}],"container-title":["Lecture Notes in Computer Science","Document Analysis and Recognition - ICDAR 2024"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-70533-5_14","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,7]],"date-time":"2024-09-07T05:05:50Z","timestamp":1725685550000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-70533-5_14"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9783031705328","9783031705335"],"references-count":26,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-70533-5_14","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024]]},"assertion":[{"value":"8 September 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"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":"Athens","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Greece","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":"30 August 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 September 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icdar2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/icdar2024.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}