{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,9]],"date-time":"2025-09-09T22:01:27Z","timestamp":1757455287539,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":26,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819962068"},{"type":"electronic","value":"9789819962075"}],"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\/978-981-99-6207-5_9","type":"book-chapter","created":{"date-parts":[[2023,9,19]],"date-time":"2023-09-19T08:45:34Z","timestamp":1695113134000},"page":"145-158","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Document Information Extraction via Global Tagging"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-4219-9909","authenticated-orcid":false,"given":"Shaojie","family":"He","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1177-3901","authenticated-orcid":false,"given":"Tianshu","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5842-7715","authenticated-orcid":false,"given":"Yaojie","family":"Lu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-5857-9663","authenticated-orcid":false,"given":"Hongyu","family":"Lin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1304-6302","authenticated-orcid":false,"given":"Xianpei","family":"Han","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0615-2569","authenticated-orcid":false,"given":"Yingfei","family":"Sun","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8750-6295","authenticated-orcid":false,"given":"Le","family":"Sun","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,9,20]]},"reference":[{"key":"9_CR1","doi-asserted-by":"publisher","unstructured":"Appalaraju, S., Jasani, B., Kota, B.U., Xie, Y., Manmatha, R.: DocFormer: end-to-end transformer for document understanding. In: 2021 IEEE\/CVF International Conference on Computer Vision, ICCV 2021, Montreal, QC, Canada, 10\u201317 October 2021, pp. 973\u2013983. IEEE (2021). https:\/\/doi.org\/10.1109\/ICCV48922.2021.00103","DOI":"10.1109\/ICCV48922.2021.00103"},{"key":"9_CR2","doi-asserted-by":"publisher","unstructured":"Cao, H., et al.: GMN: generative multi-modal network for practical document information extraction. In: Carpuat, M., de Marneffe, M., Ru\u00edz, I.V.M. (eds.) Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL 2022, Seattle, WA, United States, 10\u201315 July 2022, pp. 3768\u20133778. Association for Computational Linguistics (2022). https:\/\/doi.org\/10.18653\/v1\/2022.naacl-main.276","DOI":"10.18653\/v1\/2022.naacl-main.276"},{"key":"9_CR3","doi-asserted-by":"publisher","unstructured":"Cheng, Z., et al.: TRIE++: towards end-to-end information extraction from visually rich documents. CoRR (2022). https:\/\/doi.org\/10.48550\/arXiv.2207.06744","DOI":"10.48550\/arXiv.2207.06744"},{"key":"9_CR4","doi-asserted-by":"publisher","unstructured":"Davis, B.L., Morse, B.S., Price, B.L., Tensmeyer, C., Wigington, C., Morariu, V.I.: End-to-end document recognition and understanding with Dessurt. In: Karlinsky, L., Michaeli, T., Nishino, K. (eds.) Computer Vision - ECCV 2022 Workshops - Tel Aviv, Israel, 23\u201327 October 2022, Proceedings, Part IV. LNCS, vol. 13804, pp. 280\u2013296. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-25069-9_19","DOI":"10.1007\/978-3-031-25069-9_19"},{"key":"9_CR5","unstructured":"Denk, T.I., Reisswig, C.: BERTgrid: contextualized embedding for 2D document representation and understanding. In: Workshop on Document Intelligence at NeurIPS 2019 (2019). https:\/\/openreview.net\/forum?id=H1gsGaq9US"},{"key":"9_CR6","doi-asserted-by":"publisher","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. Proc. AAAI Conf. Artif. Intell. 36(10), 10767\u201310775 (2022). https:\/\/doi.org\/10.1609\/aaai.v36i10.21322, https:\/\/ojs.aaai.org\/index.php\/AAAI\/article\/view\/21322","DOI":"10.1609\/aaai.v36i10.21322"},{"key":"9_CR7","doi-asserted-by":"publisher","unstructured":"Hwang, W., Lee, H., Yim, J., Kim, G., Seo, M.: Cost-effective end-to-end information extraction for semi-structured document images. In: Moens, M., Huang, X., Specia, L., Yih, S.W. (eds.) Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, EMNLP 2021, Virtual Event\/Punta Cana, Dominican Republic, 7\u201311 November 2021, pp. 3375\u20133383. Association for Computational Linguistics (2021). https:\/\/doi.org\/10.18653\/v1\/2021.emnlp-main.271","DOI":"10.18653\/v1\/2021.emnlp-main.271"},{"key":"9_CR8","doi-asserted-by":"publisher","unstructured":"Hwang, W., Yim, J., Park, S., Yang, S., Seo, M.: Spatial dependency parsing for semi-structured document information extraction. In: Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021, pp. 330\u2013343. Association for Computational Linguistics, Online (2021). https:\/\/doi.org\/10.18653\/v1\/2021.findings-acl.28, https:\/\/aclanthology.org\/2021.findings-acl.28","DOI":"10.18653\/v1\/2021.findings-acl.28"},{"key":"9_CR9","doi-asserted-by":"publisher","unstructured":"Jaume, G., Kemal Ekenel, H., 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. 2, pp. 1\u20136 (2019). https:\/\/doi.org\/10.1109\/ICDARW.2019.10029","DOI":"10.1109\/ICDARW.2019.10029"},{"key":"9_CR10","doi-asserted-by":"publisher","unstructured":"Kim, G., et al.: OCR-free document understanding transformer. In: Avidan, S., Brostow, G.J., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) Computer Vision - ECCV 2022\u201317th European Conference, Tel Aviv, Israel, 23\u201327 October 2022, Proceedings, Part XXVIII. LNCS, vol. 13688, pp. 498\u2013517. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-19815-1_29","DOI":"10.1007\/978-3-031-19815-1_29"},{"key":"9_CR11","doi-asserted-by":"publisher","unstructured":"Lee, C., et al.: FormNet: structural encoding beyond sequential modeling in form document information extraction. In: Muresan, S., Nakov, P., Villavicencio, A. (eds.) Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (vol. 1: Long Papers), ACL 2022, Dublin, Ireland, 22\u201327 May 2022, pp. 3735\u20133754. Association for Computational Linguistics (2022). https:\/\/doi.org\/10.18653\/v1\/2022.acl-long.260","DOI":"10.18653\/v1\/2022.acl-long.260"},{"key":"9_CR12","doi-asserted-by":"publisher","unstructured":"Li, C., et al.: StructuralLM: structural pre-training for form understanding. In: Zong, C., Xia, F., Li, W., Navigli, R. (eds.) Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing, ACL\/IJCNLP 2021, (vol. 1: Long Papers), Virtual Event, 1\u20136 August 2021, pp. 6309\u20136318. Association for Computational Linguistics (2021). https:\/\/doi.org\/10.18653\/v1\/2021.acl-long.493","DOI":"10.18653\/v1\/2021.acl-long.493"},{"key":"9_CR13","doi-asserted-by":"publisher","unstructured":"Li, Q., et al.: Reinforcement learning-based dialogue guided event extraction to exploit argument relations. IEEE ACM Trans. Audio Speech Lang. Process. 30, 520\u2013533 (2022). https:\/\/doi.org\/10.1109\/TASLP.2021.3138670","DOI":"10.1109\/TASLP.2021.3138670"},{"key":"9_CR14","doi-asserted-by":"publisher","unstructured":"Li, Y., et al.: Structext: structured text understanding with multi-modal transformers. In: Shen, H.T., et al. (eds.) MM 2021: ACM Multimedia Conference, Virtual Event, China, 20\u201324 October 2021, pp. 1912\u20131920. ACM (2021). https:\/\/doi.org\/10.1145\/3474085.3475345","DOI":"10.1145\/3474085.3475345"},{"key":"9_CR15","doi-asserted-by":"publisher","unstructured":"Mathur, P., et al.: LayerDOC: layer-wise extraction of spatial hierarchical structure in visually-rich documents. In: IEEE\/CVF Winter Conference on Applications of Computer Vision, WACV 2023, Waikoloa, HI, USA, 2\u20137 January 2023, pp. 3599\u20133609. IEEE (2023). https:\/\/doi.org\/10.1109\/WACV56688.2023.00360","DOI":"10.1109\/WACV56688.2023.00360"},{"key":"9_CR16","unstructured":"Su, J., Lu, Y., Pan, S., Wen, B., Liu, Y.: RoFormer: enhanced transformer with rotary position embedding. CoRR abs\/2104.09864 (2021). https:\/\/arxiv.org\/abs\/2104.09864"},{"key":"9_CR17","doi-asserted-by":"publisher","unstructured":"Su, J., et al.: Global pointer: novel efficient span-based approach for named entity recognition. CoRR abs\/2208.03054 (2022). https:\/\/doi.org\/10.48550\/arXiv.2208.03054","DOI":"10.48550\/arXiv.2208.03054"},{"key":"9_CR18","doi-asserted-by":"publisher","unstructured":"Sun, K., Zhang, R., Mensah, S., Mao, Y., Liu, X.: Learning implicit and explicit multi-task interactions for information extraction. ACM Trans. Inf. Syst. 41(2), 27:1\u201327:29 (2023). https:\/\/doi.org\/10.1145\/3533020","DOI":"10.1145\/3533020"},{"key":"9_CR19","doi-asserted-by":"publisher","unstructured":"Wang, J., Jin, L., Ding, K.: LiLT: a simple yet effective language-independent layout transformer for structured document understanding. In: Muresan, S., Nakov, P., Villavicencio, A. (eds.) Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (vol. 1: Long Papers), ACL 2022, Dublin, Ireland, 22\u201327 May 2022, pp. 7747\u20137757. Association for Computational Linguistics (2022). https:\/\/doi.org\/10.18653\/v1\/2022.acl-long.534","DOI":"10.18653\/v1\/2022.acl-long.534"},{"key":"9_CR20","doi-asserted-by":"publisher","unstructured":"Wei, M., He, Y., Zhang, Q.: Robust layout-aware IE for visually rich documents with pre-trained language models. In: Huang, J.X., et al. (eds.) Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR 2020, Virtual Event, China, 25\u201330 July 2020, pp. 2367\u20132376. ACM (2020). https:\/\/doi.org\/10.1145\/3397271.3401442","DOI":"10.1145\/3397271.3401442"},{"key":"9_CR21","doi-asserted-by":"publisher","unstructured":"Wu, Z., Ying, C., Zhao, F., Fan, Z., Dai, X., Xia, R.: Grid tagging scheme for aspect-oriented fine-grained opinion extraction. In: Findings of the Association for Computational Linguistics: EMNLP 2020, pp. 2576\u20132585. Association for Computational Linguistics, Online (2020). https:\/\/doi.org\/10.18653\/v1\/2020.findings-emnlp.234, https:\/\/aclanthology.org\/2020.findings-emnlp.234","DOI":"10.18653\/v1\/2020.findings-emnlp.234"},{"key":"9_CR22","doi-asserted-by":"publisher","unstructured":"Xu, Y., et al.: LayoutLMv2: multi-modal pre-training for visually-rich document understanding. In: Proceedings of 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. Association for Computational Linguistics, Online (2021). https:\/\/doi.org\/10.18653\/v1\/2021.acl-long.201, https:\/\/aclanthology.org\/2021.acl-long.201","DOI":"10.18653\/v1\/2021.acl-long.201"},{"key":"9_CR23","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, pp. 1192\u20131200. Association for Computing Machinery, New York, NY, USA (2020). https:\/\/doi.org\/10.1145\/3394486.3403172","DOI":"10.1145\/3394486.3403172"},{"key":"9_CR24","doi-asserted-by":"publisher","unstructured":"Xu, Y., et al.: XFUND: a benchmark dataset for multilingual visually rich form understanding. In: Findings of the Association for Computational Linguistics: ACL 2022, pp. 3214\u20133224. Association for Computational Linguistics, Dublin, Ireland (2022). https:\/\/doi.org\/10.18653\/v1\/2022.findings-acl.253, https:\/\/aclanthology.org\/2022.findings-acl.253","DOI":"10.18653\/v1\/2022.findings-acl.253"},{"key":"9_CR25","doi-asserted-by":"publisher","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: 25th International Conference on Pattern Recognition, ICPR 2020, Virtual Event\/Milan, Italy, 10\u201315 January 2021, pp. 4363\u20134370. IEEE (2020). https:\/\/doi.org\/10.1109\/ICPR48806.2021.9412927","DOI":"10.1109\/ICPR48806.2021.9412927"},{"key":"9_CR26","doi-asserted-by":"publisher","unstructured":"Zhang, Z., et al.: Layout-aware information extraction for document-grounded dialogue: dataset, method and demonstration. In: Magalh\u00e3es, J., et al. (eds.) MM 2022: The 30th ACM International Conference on Multimedia, Lisboa, Portugal, 10\u201314 October 2022, pp. 7252\u20137260. ACM (2022). https:\/\/doi.org\/10.1145\/3503161.3548765","DOI":"10.1145\/3503161.3548765"}],"container-title":["Lecture Notes in Computer Science","Chinese Computational Linguistics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-99-6207-5_9","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,9,19]],"date-time":"2023-09-19T08:47:24Z","timestamp":1695113244000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-99-6207-5_9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9789819962068","9789819962075"],"references-count":26,"URL":"https:\/\/doi.org\/10.1007\/978-981-99-6207-5_9","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"20 September 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"CCL","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China National Conference on Chinese Computational Linguistics","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Harbin","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":"2023","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"3 August 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"5 August 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"cncl2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}