{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,3]],"date-time":"2026-02-03T20:45:04Z","timestamp":1770151504322,"version":"3.49.0"},"publisher-location":"New York, NY, USA","reference-count":27,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,7,18]],"date-time":"2023-07-18T00:00:00Z","timestamp":1689638400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,7,19]]},"DOI":"10.1145\/3539618.3591975","type":"proceedings-article","created":{"date-parts":[[2023,7,19]],"date-time":"2023-07-19T00:22:59Z","timestamp":1689726179000},"page":"1944-1948","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":11,"title":["DocGraphLM: Documental Graph Language Model for Information Extraction"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5806-3894","authenticated-orcid":false,"given":"Dongsheng","family":"Wang","sequence":"first","affiliation":[{"name":"JPMorgan AI Research, London, United Kingdom"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-7460-5654","authenticated-orcid":false,"given":"Zhiqiang","family":"Ma","sequence":"additional","affiliation":[{"name":"JPMorgan AI Research, New York, NY, USA"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-1908-8679","authenticated-orcid":false,"given":"Armineh","family":"Nourbakhsh","sequence":"additional","affiliation":[{"name":"JPMorgan AI Research, New York, NY, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8638-3510","authenticated-orcid":false,"given":"Kang","family":"Gu","sequence":"additional","affiliation":[{"name":"Dartmouth College, Hanover, NH, USA"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-5960-5811","authenticated-orcid":false,"given":"Sameena","family":"Shah","sequence":"additional","affiliation":[{"name":"JPMorgan AI Research, New York, NY, USA"}]}],"member":"320","published-online":{"date-parts":[[2023,7,18]]},"reference":[{"key":"e_1_3_2_2_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00103"},{"key":"e_1_3_2_2_2_1","volume-title":"Visual FUDGE: Form Understanding via Dynamic Graph Editing. CoRR","author":"Davis Brian L.","year":"2021","unstructured":"Brian L. Davis, Bryan S. Morse, Brian L. Price, Chris Tensmeyer, and Curtis Wigington. 2021. Visual FUDGE: Form Understanding via Dynamic Graph Editing. CoRR, Vol. abs\/2105.08194 (2021). showeprint[arXiv]2105.08194 https:\/\/arxiv.org\/abs\/2105.08194"},{"key":"e_1_3_2_2_3_1","volume-title":"LAMBERT: Layout-Aware language Modeling using BERT for information extraction. CoRR","author":"Garncarek \u0141ukasz","year":"2020","unstructured":"\u0141ukasz Garncarek, Rafal Powalski, Tomasz Stanislawek, Bartosz Topolski, Piotr Halama, and Filip Gralinski. 2020. LAMBERT: Layout-Aware language Modeling using BERT for information extraction. CoRR, Vol. abs\/2002.08087 (2020). [arXiv]2002.08087 https:\/\/arxiv.org\/abs\/2002.08087"},{"key":"e_1_3_2_2_4_1","volume-title":"Doc2Graph: a Task Agnostic Document Understanding Framework based on Graph Neural Networks. arXiv preprint arXiv:2208.11168","author":"Gemelli Andrea","year":"2022","unstructured":"Andrea Gemelli, Sanket Biswas, Enrico Civitelli, Josep Llad\u00f3s, and Simone Marinai. 2022. Doc2Graph: a Task Agnostic Document Understanding Framework based on Graph Neural Networks. arXiv preprint arXiv:2208.11168 (2022)."},{"key":"e_1_3_2_2_5_1","volume-title":"Inductive representation learning on large graphs. Advances in neural information processing systems","author":"Hamilton Will","year":"2017","unstructured":"Will Hamilton, Zhitao Ying, and Jure Leskovec. 2017. Inductive representation learning on large graphs. Advances in neural information processing systems, Vol. 30 (2017)."},{"key":"e_1_3_2_2_6_1","unstructured":"Teakgyu Hong DongHyun Kim Mingi Ji Wonseok Hwang Daehyun Nam and Sungrae Park. 2020. BROS: a pre-trained language model for understanding texts in document. (2020)."},{"key":"e_1_3_2_2_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548112"},{"key":"e_1_3_2_2_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDARW.2019.10029"},{"key":"e_1_3_2_2_9_1","volume-title":"Going Full-TILT Boogie on Document Understanding with Text-Image-Layout Transformer. arXiv preprint arXiv:2102.09550","author":"Powalski Rafa","year":"2021","unstructured":"Rafa l Powalski, \u0140ukasz Borchmann, and Dawid Jurkiewicz. 2021. Going Full-TILT Boogie on Document Understanding with Text-Image-Layout Transformer. arXiv preprint arXiv:2102.09550 (2021)."},{"key":"e_1_3_2_2_10_1","volume-title":"Formnet: Structural encoding beyond sequential modeling in form document information extraction. arXiv preprint arXiv:2203.08411","author":"Lee Chen-Yu","year":"2022","unstructured":"Chen-Yu Lee, Chun-Liang Li, Timothy Dozat, Vincent Perot, Guolong Su, Nan Hua, Joshua Ainslie, Renshen Wang, Yasuhisa Fujii, and Tomas Pfister. 2022. Formnet: Structural encoding beyond sequential modeling in form document information extraction. arXiv preprint arXiv:2203.08411 (2022)."},{"key":"e_1_3_2_2_11_1","doi-asserted-by":"publisher","unstructured":"Chen-Yu Lee Chun-Liang Li Chu Wang Renshen Wang Yasuhisa Fujii Siyang Qin Ashok Popat and Tomas Pfister. 2021. ROPE: Reading Order Equivariant Positional Encoding for Graph-based Document Information Extraction. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 2: Short Papers). Association for Computational Linguistics Online 314--321. https:\/\/doi.org\/10.18653\/v1\/2021.acl-short.41","DOI":"10.18653\/v1"},{"key":"e_1_3_2_2_12_1","volume-title":"Structurallm: Structural pre-training for form understanding. arXiv preprint arXiv:2105.11210","author":"Li Chenliang","year":"2021","unstructured":"Chenliang Li, Bin Bi, Ming Yan, Wei Wang, Songfang Huang, Fei Huang, and Luo Si. 2021a. Structurallm: Structural pre-training for form understanding. arXiv preprint arXiv:2105.11210 (2021)."},{"key":"e_1_3_2_2_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00560"},{"key":"e_1_3_2_2_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475345"},{"key":"e_1_3_2_2_15_1","volume-title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach. ArXiv","author":"Liu Yinhan","year":"2019","unstructured":"Yinhan Liu, Myle Ott, Naman Goyal, Jingfei Du, Mandar Joshi, Danqi Chen, Omer Levy, Mike Lewis, Luke Zettlemoyer, and Veselin Stoyanov. 2019. RoBERTa: A Robustly Optimized BERT Pretraining Approach. ArXiv, Vol. abs\/1907.11692 (2019)."},{"key":"e_1_3_2_2_16_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.580"},{"key":"e_1_3_2_2_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00225"},{"key":"e_1_3_2_2_18_1","volume-title":"Workshop on Document Intelligence at NeurIPS","author":"Park Seunghyun","year":"2019","unstructured":"Seunghyun Park, Seung Shin, Bado Lee, Junyeop Lee, Jaeheung Surh, Minjoon Seo, and Hwalsuk Lee. 2019. CORD: a consolidated receipt dataset for post-OCR parsing. In Workshop on Document Intelligence at NeurIPS 2019."},{"key":"e_1_3_2_2_19_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1"},{"key":"e_1_3_2_2_20_1","volume-title":"Markus Hagenbuchner, and Gabriele Monfardini.","author":"Scarselli Franco","year":"2008","unstructured":"Franco Scarselli, Marco Gori, Ah Chung Tsoi, Markus Hagenbuchner, and Gabriele Monfardini. 2008. The graph neural network model. IEEE transactions on neural networks, Vol. 20, 1 (2008), 61--80."},{"key":"e_1_3_2_2_21_1","volume-title":"Layoutreader: Pre-training of text and layout for reading order detection. arXiv preprint arXiv:2108.11591","author":"Wang Zilong","year":"2021","unstructured":"Zilong Wang, Yiheng Xu, Lei Cui, Jingbo Shang, and Furu Wei. 2021. Layoutreader: Pre-training of text and layout for reading order detection. arXiv preprint arXiv:2108.11591 (2021)."},{"key":"e_1_3_2_2_22_1","volume-title":"Docstruct: A multimodal method to extract hierarchy structure in document for general form understanding. arXiv preprint arXiv:2010.11685","author":"Wang Zilong","year":"2020","unstructured":"Zilong Wang, Mingjie Zhan, Xuebo Liu, and Ding Liang. 2020. Docstruct: A multimodal method to extract hierarchy structure in document for general form understanding. arXiv preprint arXiv:2010.11685 (2020)."},{"key":"e_1_3_2_2_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3403172"},{"key":"e_1_3_2_2_24_1","unstructured":"Yang Xu Yiheng Xu Tengchao Lv Lei Cui Furu Wei Guoxin Wang Yijuan Lu Dinei Florencio Cha Zhang Wanxiang Che et al. 2020b. Layoutlmv2: Multi-modal pre-training for visually-rich document understanding. arXiv preprint arXiv:2012.14740 (2020)."},{"key":"e_1_3_2_2_25_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33017370"},{"key":"e_1_3_2_2_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR48806.2021.9412927"},{"key":"e_1_3_2_2_27_1","volume-title":"Every document owns its structure: Inductive text classification via graph neural networks. arXiv preprint arXiv:2004.13826","author":"Zhang Yufeng","year":"2020","unstructured":"Yufeng Zhang, Xueli Yu, Zeyu Cui, Shu Wu, Zhongzhen Wen, and Liang Wang. 2020. Every document owns its structure: Inductive text classification via graph neural networks. arXiv preprint arXiv:2004.13826 (2020)."}],"event":{"name":"SIGIR '23: The 46th International ACM SIGIR Conference on Research and Development in Information Retrieval","location":"Taipei Taiwan","acronym":"SIGIR '23","sponsor":["SIGIR ACM Special Interest Group on Information Retrieval"]},"container-title":["Proceedings of the 46th International ACM SIGIR Conference on Research and Development in Information Retrieval"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3539618.3591975","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3539618.3591975","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T16:37:48Z","timestamp":1750178268000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3539618.3591975"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,7,18]]},"references-count":27,"alternative-id":["10.1145\/3539618.3591975","10.1145\/3539618"],"URL":"https:\/\/doi.org\/10.1145\/3539618.3591975","relation":{},"subject":[],"published":{"date-parts":[[2023,7,18]]},"assertion":[{"value":"2023-07-18","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}