{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,13]],"date-time":"2026-01-13T08:54:33Z","timestamp":1768294473839,"version":"3.49.0"},"publisher-location":"Cham","reference-count":26,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031416811","type":"print"},{"value":"9783031416828","type":"electronic"}],"license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"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":[[2023]]},"DOI":"10.1007\/978-3-031-41682-8_3","type":"book-chapter","created":{"date-parts":[[2023,8,18]],"date-time":"2023-08-18T07:02:59Z","timestamp":1692342179000},"page":"33-47","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["DAMGCN: Entity Linking in Visually Rich Documents with Dependency-Aware Multimodal Graph Convolutional Network"],"prefix":"10.1007","author":[{"given":"Yi-Ming","family":"Chen","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiang-Ting","family":"Hou","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dong-Fang","family":"Lou","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhi-Lin","family":"Liao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Cheng-Lin","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,8,19]]},"reference":[{"key":"3_CR1","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Zhang, B., Wang, R., Cao, J., Li, C., Bao, Z.: Entity relation extraction as dependency parsing in visually rich documents. arXiv preprint: arXiv:2110.09915 (2021)","DOI":"10.18653\/v1\/2021.emnlp-main.218"},{"key":"3_CR2","unstructured":"Xu, Y., et al.: LayoutXLM: multimodal pre-training for multilingual visually-rich document understanding. arXiv preprint: arXiv:2104.08836 (2021)"},{"key":"3_CR3","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":"3_CR4","unstructured":"Devlin, J., Chang, W., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. arXiv preprint: arXiv:1810.04805 (2018)"},{"key":"3_CR5","doi-asserted-by":"publisher","first-page":"143","DOI":"10.1017\/S0962492900002919","volume":"8","author":"A Pinkus","year":"1999","unstructured":"Pinkus, A.: Approximation theory of the MLP model in neural networks. Acta Numer 8, 143\u2013195 (1999)","journal-title":"Acta Numer"},{"key":"3_CR6","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: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 36, pp. 10767-10775 (2022)","DOI":"10.1609\/aaai.v36i10.21322"},{"key":"3_CR7","doi-asserted-by":"crossref","unstructured":"Wang, J., Jin, L., Ding, K.: LiLT: a simple yet effective language-independent layout transformer for structured document understanding. arXiv preprint:arXiv:2202.13669 (2022)","DOI":"10.18653\/v1\/2022.acl-long.534"},{"key":"3_CR8","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":"3_CR9","doi-asserted-by":"crossref","unstructured":"Gemelli, A., Biswas, S., Civitelli, E., Llad\u00f3s, J., Marinai, S.: Doc2Graph: a task agnostic document understanding framework based on graph neural networks. arXiv preprint: arXiv:2208.11168 (2022)","DOI":"10.1007\/978-3-031-25069-9_22"},{"key":"3_CR10","doi-asserted-by":"crossref","unstructured":"Carbonell, M., Riba, P., Villegas, M., Forn\u00e9s, A., Llad\u00f3s, J.: Named entity recognition and relation extraction with graph neural networks in semi structured documents. In: 25th International Conference on Pattern Recognition, pp. 9622\u20139627 (2021)","DOI":"10.1109\/ICPR48806.2021.9412669"},{"key":"3_CR11","unstructured":"D\u00e9jean, H., Clinchant, S., Meunier, L.: LayoutXLM vs. GNN: an empirical evaluation of relation extraction for documents. arXiv preprint: arXiv:2206.10304 (2022)"},{"key":"3_CR12","doi-asserted-by":"crossref","unstructured":"Liu, X., Gao, F., Zhang, Q., Zhao, H.: Graph convolution for multimodal information extraction from visually rich documents. arXiv preprint: arXiv:1903.11279 (2019)","DOI":"10.18653\/v1\/N19-2005"},{"key":"3_CR13","doi-asserted-by":"crossref","unstructured":"Conneau, A., et al.: Unsupervised cross-lingual representation learning at scale. arXiv preprint: arXiv:1911.02116 (2019)","DOI":"10.18653\/v1\/2020.acl-main.747"},{"key":"3_CR14","doi-asserted-by":"crossref","unstructured":"Lee, C., et al.: Formnet: structural encoding beyond sequential modeling in form document information extraction. arXiv preprint: arXiv:2203.08411 (2022)","DOI":"10.18653\/v1\/2022.acl-long.260"},{"key":"3_CR15","doi-asserted-by":"crossref","unstructured":"Davis, B., Morse, B., Cohen, S., Price, B., Tensmeyer, C.: Deep visual template-free form parsing. In: 2019 International Conference on Document Analysis and Recognition (ICDAR), pp. 134\u2013141 (2019)","DOI":"10.1109\/ICDAR.2019.00030"},{"key":"3_CR16","doi-asserted-by":"crossref","unstructured":"Chi, Z., et al.: InfoXLM: an information-theoretic framework for cross-lingual language model pre-training. arXiv preprint: arXiv:2007.07834 (2020)","DOI":"10.18653\/v1\/2021.naacl-main.280"},{"key":"3_CR17","doi-asserted-by":"crossref","unstructured":"Li, Y., et al.: StrucText: structured text understanding with multi-modal transformers. In: Proceedings of the 29th ACM International Conference on Multimedia, pp. 1912\u20131920 (2021)","DOI":"10.1145\/3474085.3475345"},{"key":"3_CR18","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"99","DOI":"10.1007\/978-3-030-86549-8_7","volume-title":"Document Analysis and Recognition - ICDAR 2021","author":"L Qiao","year":"2021","unstructured":"Qiao, L., et al.: LGPMA: Complicated table structure recognition with local and global pyramid mask alignment. In: Llad\u00f3s, J., Lopresti, D., Uchida, S. (eds.) ICDAR 2021. LNCS, vol. 12821, pp. 99\u2013114. Springer, Cham (2021). https:\/\/doi.org\/10.1007\/978-3-030-86549-8_7"},{"key":"3_CR19","unstructured":"Dang, N., Nguyen, D.: End-to-end information extraction by character-level embedding and multi-stage attentional u-net. arXiv preprint: arXiv:2106.00952 (2021)"},{"key":"3_CR20","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"570","DOI":"10.1007\/978-3-030-86331-9_37","volume-title":"Document Analysis and Recognition \u2013 ICDAR 2021","author":"W Zhao","year":"2021","unstructured":"Zhao, W., Gao, L., Yan, Z., Peng, S., Du, L., Zhang, Z.: Handwritten mathematical expression recognition with bidirectionally trained transformer. In: Llad\u00f3s, J., Lopresti, D., Uchida, S. (eds.) ICDAR 2021. LNCS, vol. 12822, pp. 570\u2013584. Springer, Cham (2021). https:\/\/doi.org\/10.1007\/978-3-030-86331-9_37"},{"key":"3_CR21","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"548","DOI":"10.1007\/978-3-030-86549-8_35","volume-title":"Document Analysis and Recognition - ICDAR 2021","author":"W Lin","year":"2021","unstructured":"Lin, W., et al.: ViBERTgrid: a jointly trained multi-modal 2D document representation for key information extraction from documents. In: Llad\u00f3s, J., Lopresti, D., Uchida, S. (eds.) ICDAR 2021. LNCS, vol. 12821, pp. 548\u2013563. Springer, Cham (2021). https:\/\/doi.org\/10.1007\/978-3-030-86549-8_35"},{"key":"3_CR22","doi-asserted-by":"crossref","unstructured":"Xie, S., Girshick, R., Doll\u00e1r, P., Tu, Z., He, K.: Aggregated residual transformations for deep neural networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1492\u20131500 (2017)","DOI":"10.1109\/CVPR.2017.634"},{"key":"3_CR23","doi-asserted-by":"crossref","unstructured":"Shi, Y., Huang, Z., Feng, S., Zhong, H., Wang, W., Sun, Y.: Masked label prediction: Unified message passing model for semi-supervised classification. arXiv preprint: arXiv:2009.03509 (2020)","DOI":"10.24963\/ijcai.2021\/214"},{"key":"3_CR24","unstructured":"Kingma, P., Ba, J.: ADAM: a method for stochastic optimization. arXiv preprint: arXiv:1412.6980 (2014)"},{"key":"3_CR25","doi-asserted-by":"crossref","unstructured":"Jaume, G., Ekenel, K., Thiran, P.: FUNSD: a dataset for form understanding in noisy scanned documents. In: 15th International Conference on Document Analysis and Recognition Workshops, vol. 2, pp. 1\u20136 (2019)","DOI":"10.1109\/ICDARW.2019.10029"},{"key":"3_CR26","doi-asserted-by":"crossref","unstructured":"Xu, Y., et al.: XFUND: a benchmark dataset for multilingual visually rich form understanding. In: Findings of the Association for Computational Linguistics, pp. 3214\u20133224 (2022)","DOI":"10.18653\/v1\/2022.findings-acl.253"}],"container-title":["Lecture Notes in Computer Science","Document Analysis and Recognition - ICDAR 2023"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-41682-8_3","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,18]],"date-time":"2023-08-18T07:16:46Z","timestamp":1692343006000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-41682-8_3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031416811","9783031416828"],"references-count":26,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-41682-8_3","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"19 August 2023","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":"San Jos\u00e9, CA","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"USA","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2023","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"21 August 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26 August 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icdar2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/icdar2023.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-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":"316","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":"154","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":"0","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":"49% - 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":"2.89","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":"1.50","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":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Number and type of other papers accepted : IJDAR track papers","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)"}}]}}