{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,25]],"date-time":"2026-06-25T17:00:51Z","timestamp":1782406851606,"version":"3.54.5"},"publisher-location":"Cham","reference-count":39,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031705328","type":"print"},{"value":"9783031705335","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\/978-3-031-70533-5_16","type":"book-chapter","created":{"date-parts":[[2024,9,7]],"date-time":"2024-09-07T05:02:25Z","timestamp":1725685345000},"page":"262-279","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["EntityLayout: Entity-Level Pre-training Language Model for\u00a0Semantic Entity Recognition and\u00a0Relation Extraction"],"prefix":"10.1007","author":[{"given":"Chun-Bo","family":"Xu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yi-Ming","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Cheng-Lin","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,9,8]]},"reference":[{"key":"16_CR1","doi-asserted-by":"crossref","unstructured":"Liu, X., Gao, F., Zhang, Q., Zhao, H.: Graph convolution for multimodal information extraction from visually rich documents (2019). arXiv preprint arXiv:1903.11279","DOI":"10.18653\/v1\/N19-2005"},{"key":"16_CR2","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: Proceedings of the 25th International Conference on Pattern Recognition (ICPR), pp. 9622\u20139627 (2021)","DOI":"10.1109\/ICPR48806.2021.9412669"},{"key":"16_CR3","doi-asserted-by":"crossref","unstructured":"Yu, W., Lu, N., Qi, X., Gong, P., Xiao, R.: PICK: processing key information extraction from documents using improved graph learning-convolutional networks. In: Proceedings of the 25th International Conference on Pattern Recognition (ICPR), pp. 4363\u20134370 (2021)","DOI":"10.1109\/ICPR48806.2021.9412927"},{"key":"16_CR4","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"},{"key":"16_CR5","doi-asserted-by":"crossref","unstructured":"Xu, Y., et\u00a0al.: LayoutLMv2: Multi-modal pre-training for visually-rich document understanding (2020). arXiv preprint arXiv:2012.14740","DOI":"10.18653\/v1\/2021.acl-long.201"},{"key":"16_CR6","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: Proceedings of the 30th ACM International Conference on Multimedia, pp. 4083\u20134091 (2022)","DOI":"10.1145\/3503161.3548112"},{"key":"16_CR7","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, pp. 7092\u20137101 (2023)","DOI":"10.1109\/CVPR52729.2023.00685"},{"key":"16_CR8","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 (2021). arXiv preprint arXiv:2110.09915","DOI":"10.18653\/v1\/2021.emnlp-main.218"},{"key":"16_CR9","doi-asserted-by":"crossref","unstructured":"Lee, C.Y., et al.: FormNet: Structural encoding beyond sequential modeling in form document information extraction (2022). arXiv preprint arXiv:2203.08411","DOI":"10.18653\/v1\/2022.acl-long.260"},{"key":"16_CR10","doi-asserted-by":"crossref","unstructured":"Davis, B., Morse, B., Cohen, S., Price, B., Tensmeyer, C.: Deep visual template-free form parsing. In: Proceedings of the International Conference on Document Analysis and Recognition (ICDAR), pp. 134\u2013141 (2019)","DOI":"10.1109\/ICDAR.2019.00030"},{"key":"16_CR11","unstructured":"D\u00e9jean, H., Clinchant, S., Meunier, J.L.: LayoutXLM vs. GNN: An empirical evaluation of relation extraction for documents (2022). arXiv preprint arXiv:2206.10304"},{"key":"16_CR12","doi-asserted-by":"publisher","unstructured":"Chen, Y.M., Hou, X.T., Lou, D.F., Liao, Z.L., Liu, C.L.: DAMGCN: entity linking in visually rich documents with dependency-aware multimodal graph convolutional network. In: Fink, G.A., Jain, R., Kise, K., Zanibbi, R. (eds.) Document Analysis and Recognition \u2013 ICDAR 2023. ICDAR 2023. LNCS, vol. 14189. Springer, Cham (2023). https:\/\/doi.org\/10.1007\/978-3-031-41682-8_3","DOI":"10.1007\/978-3-031-41682-8_3"},{"key":"16_CR13","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":"16_CR14","doi-asserted-by":"crossref","unstructured":"Jaume, G., Ekenel, H.K., Thiran, J.P.: FUNSD: a dataset for form understanding in noisy scanned documents. In: Proceedings of International Conference on Document Analysis and Recognition Workshops (ICDARW). vol.\u00a02, pp.\u00a01\u20136 (2019)","DOI":"10.1109\/ICDARW.2019.10029"},{"key":"16_CR15","unstructured":"Park, S., Shin, S., Lee, B., Lee, J., Surh, J., Seo, M., Lee, H.: CORD: a consolidated receipt dataset for post-OCR parsing. In: Workshop on Document Intelligence at NeurIPS 2019 (2019)"},{"key":"16_CR16","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: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 993\u20131003 (2021)","DOI":"10.1109\/ICCV48922.2021.00103"},{"key":"16_CR17","doi-asserted-by":"crossref","unstructured":"Li, P., et al.: SelfDoc: self-supervised document representation learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5652\u20135660 (2021)","DOI":"10.1109\/CVPR46437.2021.00560"},{"key":"16_CR18","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":"16_CR19","unstructured":"Yu, Y., et al.: StrucTexTv2: masked visual-textual prediction for document image pre-training. In: Proceedings of the 11th International Conference on Learning Representations (2023)"},{"key":"16_CR20","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.\u00a036, pp. 10767\u201310775 (2022)","DOI":"10.1609\/aaai.v36i10.21322"},{"key":"16_CR21","doi-asserted-by":"crossref","unstructured":"Wang, J., Jin, L., Ding, K.: LiLT: A simple yet effective language-independent layout transformer for structured document understanding (2022). arXiv preprint arXiv:2202.13669","DOI":"10.18653\/v1\/2022.acl-long.534"},{"key":"16_CR22","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":"16_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: Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, pp. 1192\u20131200 (2020)","DOI":"10.1145\/3394486.3403172"},{"key":"16_CR24","unstructured":"Kipf, T.N., Welling, M.: Semi-supervised classification with graph convolutional networks. In: Proceedings of the 11th International Conference on Learning Representations (2017)"},{"key":"16_CR25","unstructured":"Huang, Z., Xu, W., Yu, K.: Bidirectional LSTM-CRF models for sequence tagging (2015). arXiv preprint arXiv:1508.01991"},{"key":"16_CR26","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: BERT: Pre-training of deep bidirectional transformers for language understanding (2018). arXiv preprint arXiv:1810.04805"},{"key":"16_CR27","doi-asserted-by":"crossref","unstructured":"Liu, Z., Lin, Y., Cao, Y., Hu, H., Wei, Y., Zhang, Z., Lin, S., Guo, B.: Swin transformer: hierarchical vision transformer using shifted windows. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 10012\u201310022 (2021)","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"16_CR28","doi-asserted-by":"publisher","unstructured":"Gemelli, A., Biswas, S., Civitelli, E., Llad\u00f3s, J., Marinai, S.: Doc2Graph: a task agnostic document understanding framework based on graph neural networks. In: Karlinsky, L., Michaeli, T., Nishino, K. (eds.) Computer Vision - ECCV 2022 Workshops. ECCV 2022. LNCS, vol. 13804. Springer, Cham (2023). https:\/\/doi.org\/10.1007\/978-3-031-25069-9_22","DOI":"10.1007\/978-3-031-25069-9_22"},{"key":"16_CR29","doi-asserted-by":"crossref","unstructured":"Sun, Y., et al.: ERNIE 2.0: a continual pre-training framework for language understanding. In: Proceedings of the AAAI Conference on Artificial Intelligence. vol.\u00a034, pp. 8968\u20138975 (2020)","DOI":"10.1609\/aaai.v34i05.6428"},{"key":"16_CR30","unstructured":"Zhang, Z., Sabuncu, M.: Generalized cross entropy loss for training deep neural networks with noisy labels. In: Advances in Neural Information Processing Systems. vol.\u00a031, pp. 8778\u20138788 (2018)"},{"key":"16_CR31","unstructured":"Chung, J., Gulcehre, C., Cho, K., Bengio, Y.: Empirical evaluation of gated recurrent neural networks on sequence modeling (2014). arXiv preprint arXiv:1412.3555"},{"key":"16_CR32","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"16_CR33","doi-asserted-by":"crossref","unstructured":"Gao, T., Yao, X., Chen, D.: SimCSE: simple contrastive learning of sentence embeddings. In: Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pp. 6894\u20136910 (2021)","DOI":"10.18653\/v1\/2021.emnlp-main.552"},{"key":"16_CR34","doi-asserted-by":"crossref","unstructured":"Ruby, U., Yendapalli, V.: Binary cross entropy with deep learning technique for image classification. Int. J. Adv. Trends Comput. Sci. Eng. 9(10), 5393\u20135397 (2020)","DOI":"10.30534\/ijatcse\/2020\/175942020"},{"key":"16_CR35","unstructured":"Fan, Y., Lyu, S., Ying, Y., Hu, B.: Learning with average top-k loss. In: Advances in Neural Information Processing Systems. vol.\u00a030, pp. 497\u2013505 (2017)"},{"key":"16_CR36","doi-asserted-by":"crossref","unstructured":"Harley, A.W., Ufkes, A., Derpanis, K.G.: Evaluation of deep convolutional nets for document image classification and retrieval. In: Proceedings of the 13th International Conference on Document Analysis and Recognition (ICDAR), pp. 991\u2013995. IEEE (2015)","DOI":"10.1109\/ICDAR.2015.7333910"},{"key":"16_CR37","unstructured":"Li, C., et\u00a0al.: PP-OCRv3: More attempts for the improvement of ultra lightweight OCR system (2022). arXiv preprint arXiv:2206.03001"},{"key":"16_CR38","unstructured":"SHI, X., Chen, Z., Wang, H., Yeung, D.Y., Wong, W.K., WOO, W.C.: Convolutional LSTM network: a machine learning approach for precipitation nowcasting. In: Advances in Neural Information Processing Systems. vol.\u00a028, pp. 802\u2013810 (2015)"},{"key":"16_CR39","doi-asserted-by":"crossref","unstructured":"Wang, R., Fujii, Y., Popat, A.C.: Post-OCR paragraph recognition by graph convolutional networks. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 493\u2013502 (2022)","DOI":"10.1109\/WACV51458.2022.00259"}],"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_16","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,7]],"date-time":"2024-09-07T05:06:34Z","timestamp":1725685594000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-70533-5_16"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9783031705328","9783031705335"],"references-count":39,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-70533-5_16","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":"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"}}]}}