{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,28]],"date-time":"2026-01-28T04:02:21Z","timestamp":1769572941212,"version":"3.49.0"},"publisher-location":"Cham","reference-count":34,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030865481","type":"print"},{"value":"9783030865498","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\/978-3-030-86549-8_34","type":"book-chapter","created":{"date-parts":[[2021,9,4]],"date-time":"2021-09-04T02:05:57Z","timestamp":1630721157000},"page":"532-547","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":68,"title":["LAMBERT: Layout-Aware Language Modeling for Information Extraction"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4811-5184","authenticated-orcid":false,"given":"\u0141ukasz","family":"Garncarek","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8509-5683","authenticated-orcid":false,"given":"Rafa\u0142","family":"Powalski","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1046-7563","authenticated-orcid":false,"given":"Tomasz","family":"Stanis\u0142awek","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7126-9424","authenticated-orcid":false,"given":"Bartosz","family":"Topolski","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9010-0205","authenticated-orcid":false,"given":"Piotr","family":"Halama","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4242-9705","authenticated-orcid":false,"given":"Micha\u0142","family":"Turski","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8066-4533","authenticated-orcid":false,"given":"Filip","family":"Grali\u0144ski","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2021,9,2]]},"reference":[{"key":"34_CR1","unstructured":"Amazon: Amazon Textract (2019). https:\/\/aws.amazon.com\/textract\/. Accessed 25 Nov 2019"},{"key":"34_CR2","doi-asserted-by":"crossref","unstructured":"Bart, E., Sarkar, P.: Information extraction by finding repeated structure. In: DAS 2010 (2010)","DOI":"10.1145\/1815330.1815353"},{"key":"34_CR3","doi-asserted-by":"publisher","first-page":"102","DOI":"10.1007\/s10032-002-0084-6","volume":"6","author":"F Cesarini","year":"2003","unstructured":"Cesarini, F., Francesconi, E., Gori, M., Soda, G.: Analysis and understanding of multi-class invoices. IJDAR 6, 102\u2013114 (2003)","journal-title":"IJDAR"},{"key":"34_CR4","doi-asserted-by":"crossref","unstructured":"Dai, Z., et al.: Transformer-XL: Attentive language models beyond a fixed-length context. In: ACL (2019)","DOI":"10.18653\/v1\/P19-1285"},{"key":"34_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)"},{"key":"34_CR6","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. In: NAACL-HLT (2019)"},{"key":"34_CR7","unstructured":"Gehring, J., Auli, M., Grangier, D., Yarats, D., Dauphin, Y.N.: Convolutional sequence to sequence learning. In: ICML (2017)"},{"key":"34_CR8","unstructured":"Google: Cloud Document Understanding AI (2019). https:\/\/cloud.google.com\/document-understanding\/docs\/. Accessed 25 Nov 2019"},{"key":"34_CR9","doi-asserted-by":"publisher","unstructured":"Gururangan, S., Marasovi\u0107, A., Swayamdipta, S., Lo, K., Beltagy, I., Downey, D., Smith, N.A.: Don\u2019t stop pretraining: adapt language models to domains and tasks. In: Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pp. 8342\u20138360. Association for Computational Linguistics (2020). https:\/\/doi.org\/10.18653\/v1\/2020.acl-main.740","DOI":"10.18653\/v1\/2020.acl-main.740"},{"key":"34_CR10","doi-asserted-by":"crossref","unstructured":"Hamza, H., Bela\u00efd, Y., Bela\u00efd, A., Chaudhuri, B.: An end-to-end administrative document analysis system. In: 2008 The Eighth IAPR International Workshop on Document Analysis Systems, pp. 175\u2013182 (2008)","DOI":"10.1109\/DAS.2008.43"},{"key":"34_CR11","unstructured":"Huang, Y., et al.: Gpipe: Efficient training of giant neural networks using pipeline parallelism. In: NeurIPS (2019)"},{"key":"34_CR12","unstructured":"ICDAR: Competition on Scanned Receipts OCR and Information Extraction (2019). https:\/\/rrc.cvc.uab.es\/?ch=13. Accessed 21 Feb 2021"},{"key":"34_CR13","unstructured":"ICDAR: Leaderboard of the Information Extraction Task, Robust Reading Competition (2020). https:\/\/rrc.cvc.uab.es\/?ch=13&com=evaluation&task=3. Accessed 7 Apr 2020"},{"key":"34_CR14","doi-asserted-by":"publisher","first-page":"165","DOI":"10.1142\/S0219427902000583","volume":"15","author":"Y Ishitani","year":"2002","unstructured":"Ishitani, Y.: Model-based information extraction method tolerant of ocr errors for document images. Int. J. Comput. Process. Orient. Lang. 15, 165\u2013186 (2002)","journal-title":"Int. J. Comput. Process. Orient. Lang."},{"key":"34_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":"34_CR16","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 (2006)","DOI":"10.1145\/1148170.1148307"},{"key":"34_CR17","doi-asserted-by":"crossref","unstructured":"Liu, X., Gao, F., Zhang, Q., Zhao, H.: Graph convolution for multimodal information extraction from visually rich documents. In: NAACL-HLT (2019)","DOI":"10.18653\/v1\/N19-2005"},{"key":"34_CR18","unstructured":"Liu, Y., et al.: RoBERTa: A Robustly Optimized BERT Pretraining Approach. ArXiv arXiv:1907.11692 (2019)"},{"key":"34_CR19","doi-asserted-by":"publisher","first-page":"335","DOI":"10.1007\/s10032-010-0137-1","volume":"14","author":"E Medvet","year":"2011","unstructured":"Medvet, E., Bartoli, A., Davanzo, G.: A probabilistic approach to printed document understanding. IJDAR 14, 335\u2013347 (2011)","journal-title":"IJDAR"},{"key":"34_CR20","unstructured":"Microsoft: Cognitive Services (2019). https:\/\/azure.microsoft.com\/en-us\/services\/cognitive-services\/. Accessed 25 Nov 2019"},{"key":"34_CR21","unstructured":"Park, S., et al.: CORD: A Consolidated Receipt Dataset for Post-OCR Parsing. In: Document Intelligence Workshop at Neural Information Processing Systems (2019)"},{"key":"34_CR22","doi-asserted-by":"publisher","first-page":"543","DOI":"10.1007\/s10489-012-0348-x","volume":"37","author":"C Peanho","year":"2012","unstructured":"Peanho, C., Stagni, H., Silva, F.: Semantic information extraction from images of complex documents. Appl. Intell. 37, 543\u2013557 (2012)","journal-title":"Appl. Intell."},{"issue":"140","key":"34_CR23","first-page":"1","volume":"21","author":"C Raffel","year":"2020","unstructured":"Raffel, C., et al.: Exploring the limits of transfer learning with a unified text-to-text transformer. J. Mach. Learn. Res. 21(140), 1\u201367 (2020)","journal-title":"J. Mach. Learn. Res."},{"key":"34_CR24","doi-asserted-by":"crossref","unstructured":"Rahman, W., et al.: Integrating multimodal information in large pretrained transformers. In: ACL (2020)","DOI":"10.18653\/v1\/2020.acl-main.214"},{"key":"34_CR25","doi-asserted-by":"crossref","unstructured":"Rusinol, M., Benkhelfallah, T., Poulain d\u2019Andecy, V.: Field extraction from administrative documents by incremental structural templates. In: ICDAR (2013)","DOI":"10.1109\/ICDAR.2013.223"},{"key":"34_CR26","doi-asserted-by":"crossref","unstructured":"Shaw, P., Uszkoreit, J., Vaswani, A.: Self-attention with relative position representations. In: NAACL-HLT (2018)","DOI":"10.18653\/v1\/N18-2074"},{"key":"34_CR27","doi-asserted-by":"crossref","unstructured":"Stanis\u0142awek, T., et al.: Kleister: A novel task for information extraction involving long documents with complex layout (2021) . ArXiv arXiv:2105.05796 Accepted to ICDAR 2021","DOI":"10.1007\/978-3-030-86549-8_36"},{"key":"34_CR28","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems 30 (2017)"},{"key":"34_CR29","doi-asserted-by":"crossref","unstructured":"Wang, A., Singh, A., Michael, J., Hill, F., Levy, O., Bowman, S.R.: GLUE: a multi-task benchmark and analysis platform for natural language understanding. In: Proceedings of ICLR (2019). https:\/\/gluebenchmark.com\/. Accessed 26 Nov 2019","DOI":"10.18653\/v1\/W18-5446"},{"key":"34_CR30","unstructured":"Wolf, T., et al.: Transformers: state-of-the-art natural language processing. In: Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing: System Demonstrations, pp. 38\u201345. Association for Computational Linguistics, Online (October 2020). https:\/\/www.aclweb.org\/anthology\/2020.emnlp-demos.6"},{"key":"34_CR31","doi-asserted-by":"crossref","unstructured":"Xu, Y., et al.: LayoutLMv2: Multi-modal pre-training for visually-rich document understanding. arXiv arXiv:2012.14740 (2020)","DOI":"10.18653\/v1\/2021.acl-long.201"},{"key":"34_CR32","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":"34_CR33","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: 2020 25th International Conference on Pattern Recognition (ICPR), pp. 4363\u20134370 (2021). https:\/\/doi.org\/10.1109\/ICPR48806.2021.9412927","DOI":"10.1109\/ICPR48806.2021.9412927"},{"key":"34_CR34","doi-asserted-by":"crossref","unstructured":"Zhang, P., et al.: TRIE: end-to-end text reading and information extraction for document understanding. In: Proceedings of the 28th ACM International Conference on Multimedia (2020)","DOI":"10.1145\/3394171.3413900"}],"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\/978-3-030-86549-8_34","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,3]],"date-time":"2025-09-03T22:02:39Z","timestamp":1756936959000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-86549-8_34"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"ISBN":["9783030865481","9783030865498"],"references-count":34,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-86549-8_34","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)"}}]}}