{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,17]],"date-time":"2025-09-17T15:28:44Z","timestamp":1758122924819,"version":"3.40.3"},"publisher-location":"Cham","reference-count":28,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031416781"},{"type":"electronic","value":"9783031416798"}],"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\/978-3-031-41679-8_8","type":"book-chapter","created":{"date-parts":[[2023,8,18]],"date-time":"2023-08-18T07:02:59Z","timestamp":1692342179000},"page":"130-146","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Language Independent Neuro-Symbolic Semantic Parsing for\u00a0Form Understanding"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1352-2858","authenticated-orcid":false,"given":"Bhanu Prakash","family":"Voutharoja","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7764-431X","authenticated-orcid":false,"given":"Lizhen","family":"Qu","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8752-2132","authenticated-orcid":false,"given":"Fatemeh","family":"Shiri","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,8,19]]},"reference":[{"key":"8_CR1","doi-asserted-by":"publisher","unstructured":"Borges Oliveira, D.A., Viana, M.P.: Fast CNN-based document layout analysis. In: 2017 IEEE International Conference on Computer Vision Workshops (ICCVW), pp. 1173\u20131180 (2017). https:\/\/doi.org\/10.1109\/ICCVW.2017.142","DOI":"10.1109\/ICCVW.2017.142"},{"key":"8_CR2","doi-asserted-by":"publisher","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: 2020 25th International Conference on Pattern Recognition (ICPR), pp. 9622\u20139627 (2021). https:\/\/doi.org\/10.1109\/ICPR48806.2021.9412669","DOI":"10.1109\/ICPR48806.2021.9412669"},{"key":"8_CR3","doi-asserted-by":"publisher","unstructured":"Chi, Z., et al.: InfoXLM: an information-theoretic framework for cross-lingual language model pre-training. In: Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pp. 3576\u20133588. Association for Computational Linguistics, Online (2021). https:\/\/doi.org\/10.18653\/v1\/2021.naacl-main.280. http:\/\/aclanthology.org\/2021.naacl-main.280","DOI":"10.18653\/v1\/2021.naacl-main.280"},{"key":"8_CR4","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"416","DOI":"10.1007\/978-3-030-86549-8_27","volume-title":"Document Analysis and Recognition \u2013 ICDAR 2021","author":"B Davis","year":"2021","unstructured":"Davis, B., Morse, B., Price, B., Tensmeyer, C., Wiginton, C.: Visual FUDGE: form understanding via dynamic graph editing. In: Llad\u00f3s, J., Lopresti, D., Uchida, S. (eds.) ICDAR 2021. LNCS, vol. 12821, pp. 416\u2013431. Springer, Cham (2021). https:\/\/doi.org\/10.1007\/978-3-030-86549-8_27"},{"key":"8_CR5","doi-asserted-by":"crossref","unstructured":"Davis, B.L., Morse, B., Cohen, S.D., Price, B.L., 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":"8_CR6","unstructured":"D\u00e9jean, H., Clinchant, S., Meunier, J.: Layoutxlm vs. GNN: an empirical evaluation of relation extraction for documents. CoRR abs\/2206.10304 (2022)"},{"key":"8_CR7","unstructured":"Denk, T.I., Reisswig, C.: BERTgrid: contextualized embedding for 2D document representation and understanding. In: Workshop on Document Intelligence at NeurIPS 2019 (2019). http:\/\/openreview.net\/forum?id=H1gsGaq9US"},{"key":"8_CR8","unstructured":"Domke, J.: Structured learning via logistic regression. In: Advances in Neural Information Processing Systems, vol. 26 (2013)"},{"key":"8_CR9","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 (2022). https:\/\/doi.org\/10.48550\/ARXIV.2208.11168. http:\/\/arxiv.org\/abs\/2208.11168","DOI":"10.48550\/ARXIV.2208.11168"},{"key":"8_CR10","unstructured":"Hamilton, W., Ying, Z., Leskovec, J.: Inductive representation learning on large graphs. In: Advances in Neural Information Processing Systems, vol. 30 (2017)"},{"key":"8_CR11","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: Magalh\u00e3es, J., et al. (eds.) MM 2022: The 30th ACM International Conference on Multimedia, Lisboa, Portugal, 10\u201314 October 2022, pp. 4083\u20134091. ACM (2022)","DOI":"10.1145\/3503161.3548112"},{"key":"8_CR12","doi-asserted-by":"crossref","unstructured":"Jaume, G., Ekenel, H.K., Thiran, J.: FUNSD: a dataset for form understanding in noisy scanned documents. In: 2nd International Workshop on Open Services and Tools for Document Analysis, OST@ICDAR 2019, Sydney, Australia, 22\u201325 September 2019, pp. 1\u20136. IEEE (2019)","DOI":"10.1109\/ICDARW.2019.10029"},{"key":"8_CR13","doi-asserted-by":"publisher","unstructured":"Katti, A.R., et al.: Chargrid: towards understanding 2D documents. In: Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, Brussels, Belgium, pp. 4459\u20134469. Association for Computational Linguistics (2018). https:\/\/doi.org\/10.18653\/v1\/D18-1476. http:\/\/aclanthology.org\/D18-1476","DOI":"10.18653\/v1\/D18-1476"},{"key":"8_CR14","unstructured":"Kipf, T.N., Welling, M.: Semi-supervised classification with graph convolutional networks. In: International Conference on Learning Representations (2017). http:\/\/openreview.net\/forum?id=SJU4ayYgl"},{"key":"8_CR15","doi-asserted-by":"publisher","unstructured":"Li, C., et al.: StructuralLM: structural pre-training for form understanding. In: Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), pp. 6309\u20136318. Association for Computational Linguistics, Online (2021). https:\/\/doi.org\/10.18653\/v1\/2021.acl-long.493. http:\/\/aclanthology.org\/2021.acl-long.493","DOI":"10.18653\/v1\/2021.acl-long.493"},{"key":"8_CR16","doi-asserted-by":"crossref","unstructured":"Li, P., et al.: Selfdoc: self-supervised document representation learning. In: 2021 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 5648\u20135656 (2021)","DOI":"10.1109\/CVPR46437.2021.00560"},{"key":"8_CR17","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 \u2013 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":"8_CR18","unstructured":"Mindee: docTR: document text recognition (2021). http:\/\/github.com\/mindee\/doctr"},{"key":"8_CR19","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"732","DOI":"10.1007\/978-3-030-86331-9_47","volume-title":"Document Analysis and Recognition \u2013 ICDAR 2021","author":"R Powalski","year":"2021","unstructured":"Powalski, R., Borchmann, \u0141, Jurkiewicz, D., Dwojak, T., Pietruszka, M., Pa\u0142ka, G.: Going full-TILT boogie on document understanding with text-image-layout transformer. In: Llad\u00f3s, J., Lopresti, D., Uchida, S. (eds.) ICDAR 2021. LNCS, vol. 12822, pp. 732\u2013747. Springer, Cham (2021). https:\/\/doi.org\/10.1007\/978-3-030-86331-9_47"},{"key":"8_CR20","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"649","DOI":"10.1007\/978-3-030-58604-1_39","volume-title":"Computer Vision \u2013 ECCV 2020","author":"M Sarkar","year":"2020","unstructured":"Sarkar, M., Aggarwal, M., Jain, A., Gupta, H., Krishnamurthy, B.: Document structure extraction using prior based high resolution hierarchical semantic segmentation. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12373, pp. 649\u2013666. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58604-1_39"},{"key":"8_CR21","doi-asserted-by":"crossref","unstructured":"Siegel, N., Lourie, N., Power, R., Ammar, W.: Extracting scientific figures with distantly supervised neural networks. In: Proceedings of the 18th ACM\/IEEE on Joint Conference on Digital Libraries (2018)","DOI":"10.1145\/3197026.3197040"},{"key":"8_CR22","unstructured":"Veli\u010dkovi\u0107, P., Cucurull, G., Casanova, A., Romero, A., Li\u00f2, P., Bengio, Y.: Graph attention networks. In: International Conference on Learning Representations (2018). http:\/\/openreview.net\/forum?id=rJXMpikCZ"},{"key":"8_CR23","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: Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), Dublin, Ireland, pp. 7747\u20137757. Association for Computational Linguistics (2022). https:\/\/doi.org\/10.18653\/v1\/2022.acl-long.534. http:\/\/aclanthology.org\/2022.acl-long.534","DOI":"10.18653\/v1\/2022.acl-long.534"},{"key":"8_CR24","doi-asserted-by":"publisher","unstructured":"Wang, W., et al.: Mmlayout: multi-grained multimodal transformer for document understanding. In: Proceedings of the 30th ACM International Conference on Multimedia, MM 2022, pp. 4877\u20134886. Association for Computing Machinery, New York (2022). https:\/\/doi.org\/10.1145\/3503161.3548406","DOI":"10.1145\/3503161.3548406"},{"key":"8_CR25","doi-asserted-by":"crossref","unstructured":"Xu, Y., et al.: LayoutLMv2: multi-modal pre-training for visually-rich document 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, (Volume 1: Long Papers), Virtual Event, 1\u20136 August 2021, pp. 2579\u20132591. Association for Computational Linguistics (2021)","DOI":"10.18653\/v1\/2021.acl-long.201"},{"key":"8_CR26","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. CoRR abs\/1912.13318 (2019)","DOI":"10.1145\/3394486.3403172"},{"key":"8_CR27","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, Dublin, Ireland, pp. 3214\u20133224. Association for Computational Linguistics (2022). https:\/\/doi.org\/10.18653\/v1\/2022.findings-acl.253. http:\/\/aclanthology.org\/2022.findings-acl.253","DOI":"10.18653\/v1\/2022.findings-acl.253"},{"key":"8_CR28","doi-asserted-by":"crossref","unstructured":"Yang, X., Yumer, E., Asente, P., Kraley, M., Kifer, D., Giles, C.L.: Learning to extract semantic structure from documents using multimodal fully convolutional neural networks. 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 4342\u20134351 (2017)","DOI":"10.1109\/CVPR.2017.462"}],"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\/978-3-031-41679-8_8","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,18]],"date-time":"2023-08-18T07:24:15Z","timestamp":1692343455000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-41679-8_8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031416781","9783031416798"],"references-count":28,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-41679-8_8","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":"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)"}}]}}