{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T18:29:27Z","timestamp":1777487367285,"version":"3.51.4"},"publisher-location":"Cham","reference-count":25,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031705458","type":"print"},{"value":"9783031705465","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\/978-3-031-70546-5_10","type":"book-chapter","created":{"date-parts":[[2024,9,10]],"date-time":"2024-09-10T05:02:47Z","timestamp":1725944567000},"page":"160-174","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["A LayoutLMv3-Based Model for\u00a0Enhanced Relation Extraction in\u00a0Visually-Rich Documents"],"prefix":"10.1007","author":[{"given":"Wiam","family":"Adnan","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Joel","family":"Tang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yassine Bel Khayat","family":"Zouggari","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Seif Edinne","family":"Laatiri","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Laurent","family":"Lam","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fabien","family":"Caspani","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,9,11]]},"reference":[{"key":"10_CR1","doi-asserted-by":"publisher","unstructured":"Baldini\u00a0Soares, L., FitzGerald, N., Ling, J., Kwiatkowski, T.: Matching the blanks: distributional similarity for relation learning. In: Korhonen, A., Traum, D., M\u00e0rquez, L. (eds.) Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pp. 2895\u20132905. Association for Computational Linguistics, Florence, Italy, July 2019. https:\/\/doi.org\/10.18653\/v1\/P19-1279, https:\/\/aclanthology.org\/P19-1279","DOI":"10.18653\/v1\/P19-1279"},{"key":"10_CR2","doi-asserted-by":"publisher","unstructured":"Brill, E.: A simple rule-based part of speech tagger. In: Third Conference on Applied Natural Language Processing, pp. 152\u2013155. Association for Computational Linguistics, Trento, Italy, March 1992. https:\/\/doi.org\/10.3115\/974499.974526, https:\/\/aclanthology.org\/A92-1021","DOI":"10.3115\/974499.974526"},{"key":"10_CR3","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding (2019)"},{"key":"10_CR4","doi-asserted-by":"publisher","unstructured":"Fang, Z., Cao, Y., Li, Q., Zhang, D., Zhang, Z., Liu, Y.: Joint entity linking with deep reinforcement learning. In: The World Wide Web Conference, WWW 2019, pp. 438\u2013447. Association for Computing Machinery, New York, NY, USA (2019). https:\/\/doi.org\/10.1145\/3308558.3313517","DOI":"10.1145\/3308558.3313517"},{"key":"10_CR5","doi-asserted-by":"publisher","unstructured":"Fang, Z., Cao, Y., Li, R., Zhang, Z., Liu, Y., Wang, S.: High quality candidate generation and sequential graph attention network for entity linking. In: Proceedings of The Web Conference 2020, WWW 2020, pp. 640\u2013650. Association for Computing Machinery, New York, NY, USA (2020). https:\/\/doi.org\/10.1145\/3366423.3380146","DOI":"10.1145\/3366423.3380146"},{"key":"10_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 (2022)","DOI":"10.1609\/aaai.v36i10.21322"},{"key":"10_CR7","doi-asserted-by":"publisher","unstructured":"Huang, Y.Y., Wang, W.Y.: Deep residual learning for weakly-supervised relation extraction. In: Palmer, M., Hwa, R., Riedel, S. (eds.) Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, pp. 1803\u20131807. Association for Computational Linguistics, Copenhagen, Denmark, September 2017. https:\/\/doi.org\/10.18653\/v1\/D17-1191, https:\/\/aclanthology.org\/D17-1191","DOI":"10.18653\/v1\/D17-1191"},{"key":"10_CR8","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, NY, USA (2022). https:\/\/doi.org\/10.1145\/3503161.3548112","DOI":"10.1145\/3503161.3548112"},{"key":"10_CR9","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.\u00a01\u20136. IEEE (2019)","DOI":"10.1109\/ICDARW.2019.10029"},{"key":"10_CR10","doi-asserted-by":"publisher","unstructured":"Li, Y., et al.: StrucTexT: structured text understanding with multi-modal transformers. In: Proceedings of the 29th ACM International Conference on Multimedia, MM 2021, pp. 1912\u20131920. Association for Computing Machinery, New York, NY, USA (2021). https:\/\/doi.org\/10.1145\/3474085.3475345","DOI":"10.1145\/3474085.3475345"},{"key":"10_CR11","doi-asserted-by":"crossref","unstructured":"Luo, C., Cheng, C., Zheng, Q., Yao, C.: GeoLayoutLM: geometric pre-training for visual information extraction. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 7092\u20137101, June 2023","DOI":"10.1109\/CVPR52729.2023.00685"},{"key":"10_CR12","doi-asserted-by":"crossref","unstructured":"Ma, Y., Wang, A., Okazaki, N.: DREEAM: guiding attention with evidence for improving document-level relation extraction (2023)","DOI":"10.18653\/v1\/2023.eacl-main.145"},{"key":"10_CR13","unstructured":"Park, S., et al.: CORD: a consolidated receipt dataset for Post-OCR parsing. In: Workshop on Document Intelligence at NeurIPS 2019 (2019)"},{"key":"10_CR14","unstructured":"Ramshaw, L.A., Marcus, M.P.: Text chunking using transformation-based learning (1995)"},{"key":"10_CR15","unstructured":"Vu, H.M., Nguyen, D.T.N.: Revising FUNSD dataset for key-value detection in document images. arXiv preprint arXiv:2010.05322 (2020)"},{"key":"10_CR16","doi-asserted-by":"publisher","unstructured":"Wang, C., Liu, X., Chen, Z., Hong, H., Tang, J., Song, D.: DeepStruct: pretraining of language models for structure prediction. In: Muresan, S., Nakov, P., Villavicencio, A. (eds.) Findings of the Association for Computational Linguistics: ACL 2022, pp. 803\u2013823. Association for Computational Linguistics, Dublin, Ireland, May 2022. https:\/\/doi.org\/10.18653\/v1\/2022.findings-acl.67, https:\/\/aclanthology.org\/2022.findings-acl.67","DOI":"10.18653\/v1\/2022.findings-acl.67"},{"key":"10_CR17","doi-asserted-by":"publisher","unstructured":"Wang, R., et al.: K-Adapter: infusing knowledge into pre-trained models with adapters. In: Zong, C., Xia, F., Li, W., Navigli, R. (eds.) Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021, pp. 1405\u20131418. Association for Computational Linguistics, Online, August 2021. https:\/\/doi.org\/10.18653\/v1\/2021.findings-acl.121, https:\/\/aclanthology.org\/2021.findings-acl.121","DOI":"10.18653\/v1\/2021.findings-acl.121"},{"key":"10_CR18","doi-asserted-by":"publisher","unstructured":"Wang, Z., Zhan, M., Liu, X., Liang, D.: DocStruct: a multimodal method to extract hierarchy structure in document for general form understanding. In: Cohn, T., He, Y., Liu, Y. (eds.) Findings of the Association for Computational Linguistics: EMNLP 2020, pp. 898\u2013908. Association for Computational Linguistics, Online, November 2020. https:\/\/doi.org\/10.18653\/v1\/2020.findings-emnlp.80, https:\/\/aclanthology.org\/2020.findings-emnlp.80","DOI":"10.18653\/v1\/2020.findings-emnlp.80"},{"key":"10_CR19","doi-asserted-by":"crossref","unstructured":"Xu, Y., et al.: LayoutLMv2: multi-modal pre-training for visually-rich document understanding (2022)","DOI":"10.18653\/v1\/2021.acl-long.201"},{"key":"10_CR20","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, KDD 2020. ACM, August 2020. https:\/\/doi.org\/10.1145\/3394486.3403172","DOI":"10.1145\/3394486.3403172"},{"key":"10_CR21","doi-asserted-by":"publisher","unstructured":"Zhang, Y., Bo, Z., Wang, R., Cao, J., Li, C., Bao, Z.: Entity relation extraction as dependency parsing in visually rich documents. 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. 2759\u20132768. Association for Computational Linguistics, Online and Punta Cana, Dominican Republic, November 2021. https:\/\/doi.org\/10.18653\/v1\/2021.emnlp-main.218, https:\/\/aclanthology.org\/2021.emnlp-main.218","DOI":"10.18653\/v1\/2021.emnlp-main.218"},{"key":"10_CR22","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Zhong, V., Chen, D., Angeli, G., Manning, C.D.: Position-aware attention and supervised data improve slot filling. In: Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing (EMNLP 2017), pp. 35\u201345 (2017). https:\/\/nlp.stanford.edu\/pubs\/zhang2017tacred.pdf","DOI":"10.18653\/v1\/D17-1004"},{"key":"10_CR23","doi-asserted-by":"publisher","unstructured":"Zhang, Y., Zhong, V., Chen, D., Angeli, G., Manning, C.D.: Position-aware attention and supervised data improve slot filling. In: Palmer, M., Hwa, R., Riedel, S. (eds.) Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, pp. 35\u201345. Association for Computational Linguistics, Copenhagen, Denmark, September 2017. https:\/\/doi.org\/10.18653\/v1\/D17-1004, https:\/\/aclanthology.org\/D17-1004","DOI":"10.18653\/v1\/D17-1004"},{"key":"10_CR24","unstructured":"Zhou, W., Chen, M.: An improved baseline for sentence-level relation extraction. In: He, Y., Ji, H., Li, S., Liu, Y., Chang, C.H. (eds.) Proceedings of the 2nd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 12th International Joint Conference on Natural Language Processing (Volume 2: Short Papers), pp. 161\u2013168. Association for Computational Linguistics, Online Only, November 2022. https:\/\/aclanthology.org\/2022.aacl-short.21"},{"key":"10_CR25","doi-asserted-by":"crossref","unstructured":"Zhou, W., Huang, K., Ma, T., Huang, J.: Document-level relation extraction with adaptive thresholding and localized context pooling. In: Proceedings of the AAAI Conference on Artificial Intelligence (2021)","DOI":"10.1609\/aaai.v35i16.17717"}],"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\/978-3-031-70546-5_10","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,10]],"date-time":"2024-09-10T05:04:32Z","timestamp":1725944672000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-70546-5_10"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9783031705458","9783031705465"],"references-count":25,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-70546-5_10","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":"11 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"}}]}}