{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,9]],"date-time":"2026-03-09T08:26:19Z","timestamp":1773044779316,"version":"3.50.1"},"publisher-location":"Cham","reference-count":30,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030863302","type":"print"},{"value":"9783030863319","type":"electronic"}],"license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"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":[[2021]]},"DOI":"10.1007\/978-3-030-86331-9_54","type":"book-chapter","created":{"date-parts":[[2021,9,4]],"date-time":"2021-09-04T02:05:57Z","timestamp":1630721157000},"page":"838-853","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["DeepCPCFG: Deep Learning and\u00a0Context Free Grammars for\u00a0End-to-End Information Extraction"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9809-1152","authenticated-orcid":false,"given":"Freddy C.","family":"Chua","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2663-1647","authenticated-orcid":false,"given":"Nigel P.","family":"Duffy","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2021,9,2]]},"reference":[{"key":"54_CR1","unstructured":"Alvarez-Melis, D., Jaakkola, T.S.: Tree-structured decoding with doubly-recurrent neural networks. In: ICLR (2017)"},{"key":"54_CR2","doi-asserted-by":"crossref","unstructured":"Blanchard, J., Bela\u00efd, Y., Bela\u00efd, A.: Automatic generation of a custom corpora for invoice analysis and recognition. In: ICDARW (2019)","DOI":"10.1109\/ICDARW.2019.60121"},{"key":"54_CR3","unstructured":"Cole, R.: Converting CFGs to CNF (Chomsky normal form) (2007)"},{"key":"54_CR4","doi-asserted-by":"crossref","unstructured":"Collins, M.: Discriminative training methods for hidden Markov models: theory and experiments with perceptron algorithms. In: EMNLP (2002)","DOI":"10.3115\/1118693.1118694"},{"key":"54_CR5","unstructured":"Denk, T.I., Reisswig, C.: Bertgrid: contextualized embedding for 2D document representation and understanding. In: NeurIPS Document Intelligence Workshop (2019)"},{"key":"54_CR6","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. In: ACL-HLT (2019)"},{"key":"54_CR7","doi-asserted-by":"crossref","unstructured":"Drozdov, A., Verga, P., Yadav, M., Iyyer, M., McCallum, A.: Unsupervised latent tree induction with deep inside-outside recursive auto-encoders. In: ACL-HLT (2019)","DOI":"10.18653\/v1\/N19-1116"},{"key":"54_CR8","unstructured":"Gralinski, F., et al.: Kleister: a novel task for information extraction involving long documents with complex layout. arXiv abs\/2003.02356 (2020)"},{"key":"54_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: ICDAR-OST (2019)","DOI":"10.1109\/ICDARW.2019.10029"},{"key":"54_CR10","unstructured":"Harer, J., Reale, C., Chin, P.: Tree-transformer: a transformer-based method for correction of tree-structured data (2019)"},{"key":"54_CR11","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: ICDAR (2015)","DOI":"10.1109\/ICDAR.2015.7333910"},{"key":"54_CR12","doi-asserted-by":"crossref","unstructured":"Huang, Z., et al.: ICDAR 2019 competition on scanned receipt OCR and information extraction. In: ICDAR (2019)","DOI":"10.1109\/ICDAR.2019.00244"},{"key":"54_CR13","unstructured":"Hwang, W., et al.: Post-OCR parsing: building simple and robust parser via bio tagging. arXiv (2019)"},{"key":"54_CR14","doi-asserted-by":"crossref","unstructured":"Hwang, W., Yim, J., Park, S., Yang, S., Seo, M.: Spatial dependency parsing for semi-structured document information extraction. In: ACL-IJCNLP (2021)","DOI":"10.18653\/v1\/2021.findings-acl.28"},{"key":"54_CR15","doi-asserted-by":"crossref","unstructured":"Katti, A.R., et al.: Chargrid: towards understanding 2D documents. In: EMNLP (2018)","DOI":"10.18653\/v1\/D18-1476"},{"key":"54_CR16","unstructured":"Lafferty, J.D., McCallum, A., Pereira, F.C.N.: Conditional random fields: probabilistic models for segmenting and labeling sequence data. In: ICML (2001)"},{"issue":"1","key":"54_CR17","doi-asserted-by":"publisher","first-page":"35","DOI":"10.1016\/0885-2308(90)90022-X","volume":"4","author":"K Lari","year":"1990","unstructured":"Lari, K., Young, S.: The estimation of stochastic context-free grammars using the inside-outside algorithm. Comput. Speech Lang. 4(1), 35\u201356 (1990)","journal-title":"Comput. Speech Lang."},{"key":"54_CR18","doi-asserted-by":"crossref","unstructured":"Liang, P., Narasimhan, M., Shilman, M., Viola, P.: Efficient geometric algorithms for parsing in two dimensions. In: ICDAR (2005)","DOI":"10.1109\/ICDAR.2005.98"},{"key":"54_CR19","doi-asserted-by":"crossref","unstructured":"Majumder, B.P., Potti, N., Tata, S., Wendt, J.B., Zhao, Q., Najork, M.: Representation learning for information extraction from form-like documents. In: ACL (2020)","DOI":"10.18653\/v1\/2020.acl-main.580"},{"issue":"2","key":"54_CR20","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/2543581.2543593","volume":"46","author":"RWD Pedro","year":"2013","unstructured":"Pedro, R.W.D., Nunes, F.L.S., Machado-Lima, A.: Using grammars for pattern recognition in images: a systematic review. ACM Comput. Surv. 46(2), 1\u201334 (2013)","journal-title":"ACM Comput. Surv."},{"key":"54_CR21","doi-asserted-by":"crossref","unstructured":"Shilman, M., Liang, P., Viola, P.: Learning non-generative grammatical models for document analysis. In: ICCV (2005)","DOI":"10.1109\/ICCV.2005.140"},{"key":"54_CR22","unstructured":"Subramani, N., Matton, A., Greaves, M., Lam, A.: A survey of deep learning approaches for OCR and document understanding (2020)"},{"key":"54_CR23","unstructured":"Sutton, C., McCallum, A.: Conditional probabilistic context-free grammars. Ph.D. thesis, University of Massachusetts Amherst (2004)"},{"key":"54_CR24","doi-asserted-by":"publisher","first-page":"277","DOI":"10.1007\/978-1-4615-3986-5_18","volume-title":"Current Issues in Parsing Technology","author":"M Tomita","year":"1991","unstructured":"Tomita, M.: Parsing 2-dimensional language. In: Tomita, M. (ed.) Current Issues in Parsing Technology, pp. 277\u2013289. Springer, Boston (1991). https:\/\/doi.org\/10.1007\/978-1-4615-3986-5_18"},{"key":"54_CR25","unstructured":"Vaswani, A., et al.: Attention is all you need. In: NeurIPS (2017)"},{"key":"54_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. In: SIGKDD (2020)","DOI":"10.1145\/3394486.3403172"},{"key":"54_CR27","unstructured":"Yu, W., Lu, N., Qi, X., Gong, P., Xiao, R.: Pick: processing key information extraction from documents using improved graph learning-convolutional networks (2020)"},{"issue":"6","key":"54_CR28","doi-asserted-by":"publisher","first-page":"1245","DOI":"10.1137\/0218082","volume":"18","author":"K Zhang","year":"1989","unstructured":"Zhang, K., Shasha, D.: Simple fast algorithms for the editing distance between trees and related problems. SIAM J. Comput. 18(6), 1245\u20131262 (1989)","journal-title":"SIAM J. Comput."},{"key":"54_CR29","unstructured":"Zhao, Y., Zhu, S.C.: Image parsing via stochastic scene grammar. In: NeurIPS (2011)"},{"key":"54_CR30","unstructured":"Zhu, L.L., Chen, Y., Lin, Y., Lin, C., Yuille, A.: Recursive segmentation and recognition templates for 2D parsing. In: NeurIPS (2008)"}],"container-title":["Lecture Notes in Computer Science","Document Analysis and Recognition \u2013 ICDAR 2021"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-86331-9_54","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,3]],"date-time":"2025-09-03T22:03:41Z","timestamp":1756937021000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-86331-9_54"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"ISBN":["9783030863302","9783030863319"],"references-count":30,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-86331-9_54","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021]]},"assertion":[{"value":"2 September 2021","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":"Lausanne","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Switzerland","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2021","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"5 September 2021","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"10 September 2021","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"16","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icdar2021","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/iapr.org\/icdar2021","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":"340","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":"182","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":"54% - 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":"2.9","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":"4.9","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":"Additionally, 13 competition reports are included.","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)"}}]}}