{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,1]],"date-time":"2025-12-01T06:38:15Z","timestamp":1764571095713,"version":"3.40.3"},"publisher-location":"Cham","reference-count":37,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031424472"},{"type":"electronic","value":"9783031424489"}],"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\/978-3-031-42448-9_21","type":"book-chapter","created":{"date-parts":[[2023,9,10]],"date-time":"2023-09-10T23:02:21Z","timestamp":1694386941000},"page":"276-293","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Overview of\u00a0DocILE 2023: Document Information Localization and\u00a0Extraction"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6687-1210","authenticated-orcid":false,"given":"\u0160t\u011bp\u00e1n","family":"\u0160imsa","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2606-4470","authenticated-orcid":false,"given":"Michal","family":"U\u0159i\u010d\u00e1\u0159","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6321-0131","authenticated-orcid":false,"given":"Milan","family":"\u0160ulc","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9373-529X","authenticated-orcid":false,"given":"Yash","family":"Patel","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8964-2135","authenticated-orcid":false,"given":"Ahmed","family":"Hamdi","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0124-9348","authenticated-orcid":false,"given":"Mat\u011bj","family":"Koci\u00e1n","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0197-7134","authenticated-orcid":false,"given":"Maty\u00e1\u0161","family":"Skalick\u00fd","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0863-4844","authenticated-orcid":false,"given":"Ji\u0159\u00ed","family":"Matas","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6160-3356","authenticated-orcid":false,"given":"Antoine","family":"Doucet","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0123-439X","authenticated-orcid":false,"given":"Micka\u00ebl","family":"Coustaty","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8762-4454","authenticated-orcid":false,"given":"Dimosthenis","family":"Karatzas","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,9,11]]},"reference":[{"doi-asserted-by":"crossref","unstructured":"Davis, B., Morse, B., Cohen, S., Price, B., Tensmeyer, C.: Deep visual template-free form parsing. In: ICDAR (2019)","key":"21_CR1","DOI":"10.1109\/ICDAR.2019.00030"},{"doi-asserted-by":"crossref","unstructured":"Hammami, M., H\u00e9roux, P., Adam, S., d\u2019Andecy, V.P.: One-shot field spotting on colored forms using subgraph isomorphism. In: ICDAR (2015)","key":"21_CR2","DOI":"10.1109\/ICDAR.2015.7333829"},{"doi-asserted-by":"crossref","unstructured":"Herzig, J., Nowak, P.K., M\u00fcller, T., Piccinno, F., Eisenschlos, J.M.: Tapas: weakly supervised table parsing via pre-training. arXiv (2020)","key":"21_CR3","DOI":"10.18653\/v1\/2020.acl-main.398"},{"doi-asserted-by":"crossref","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. In: AAAI (2022)","key":"21_CR4","DOI":"10.1609\/aaai.v36i10.21322"},{"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: ACM-MM (2022)","key":"21_CR5","DOI":"10.1145\/3503161.3548112"},{"doi-asserted-by":"crossref","unstructured":"Huang, Z., et al.: ICDAR2019 competition on scanned receipt OCR and information extraction. In: ICDAR (2019)","key":"21_CR6","DOI":"10.1109\/ICDAR.2019.00244"},{"unstructured":"Jocher, G., Chaurasia, A., Qiu, J.: YOLO by Ultralytics (2023). https:\/\/github.com\/ultralytics\/ultralytics","key":"21_CR7"},{"doi-asserted-by":"crossref","unstructured":"Katti, A.R., et al.: CharGrid: towards understanding 2D documents. In: Riloff, E., Chiang, D., Hockenmaier, J., Tsujii, J. (eds.) Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, Brussels, Belgium, 31 October\u20134 November 2018, pp. 4459\u20134469. Association for Computational Linguistics (2018). https:\/\/aclanthology.org\/D18-1476\/","key":"21_CR8","DOI":"10.18653\/v1\/D18-1476"},{"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: SIGIR (2006)","key":"21_CR9","DOI":"10.1145\/1148170.1148307"},{"key":"21_CR10","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":"21_CR11","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"144","DOI":"10.1007\/978-3-030-21074-8_12","volume-title":"Computer Vision \u2013 ACCV 2018 Workshops","author":"D Lohani","year":"2019","unstructured":"Lohani, D., Bela\u00efd, A., Bela\u00efd, Y.: An invoice reading system using a graph convolutional network. In: Carneiro, G., You, S. (eds.) ACCV 2018. LNCS, vol. 11367, pp. 144\u2013158. Springer, Cham (2019). https:\/\/doi.org\/10.1007\/978-3-030-21074-8_12"},{"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)","key":"21_CR12","DOI":"10.18653\/v1\/2020.acl-main.580"},{"doi-asserted-by":"crossref","unstructured":"Mathew, M., Bagal, V., Tito, R., Karatzas, D., Valveny, E., Jawahar, C.: InfographicVQA. In: WACV (2022)","key":"21_CR13","DOI":"10.1109\/WACV51458.2022.00264"},{"doi-asserted-by":"crossref","unstructured":"Mathew, M., Karatzas, D., Jawahar, C.: DocVQA: a dataset for VQA on document images. In: WACV (2021)","key":"21_CR14","DOI":"10.1109\/WACV48630.2021.00225"},{"unstructured":"Mindee: docTR: Document Text Recognition. https:\/\/github.com\/mindee\/doctr (2021)","key":"21_CR15"},{"unstructured":"Olejniczak, K., \u0160ulc, M.: Text detection forgot about document OCR. In: CVWW (2023)","key":"21_CR16"},{"key":"21_CR17","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"},{"doi-asserted-by":"crossref","unstructured":"Riba, P., Dutta, A., Goldmann, L., Forn\u00e9s, A., Ramos, O., Llad\u00f3s, J.: Table detection in invoice documents by graph neural networks. In: ICDAR (2019)","key":"21_CR18","DOI":"10.1109\/ICDAR.2019.00028"},{"issue":"3","key":"21_CR19","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1007\/s11263-015-0816-y","volume":"115","author":"O Russakovsky","year":"2015","unstructured":"Russakovsky, O., et al.: ImageNet large scale visual recognition challenge. Int. J. Comput. Vis. 115(3), 211\u2013252 (2015). https:\/\/doi.org\/10.1007\/s11263-015-0816-y","journal-title":"Int. J. Comput. Vis."},{"doi-asserted-by":"crossref","unstructured":"Schreiber, S., Agne, S., Wolf, I., Dengel, A., Ahmed, S.: DeepDeSRT: deep learning for detection and structure recognition of tables in document images. In: ICDAR (2017)","key":"21_CR20","DOI":"10.1109\/ICDAR.2017.192"},{"key":"21_CR21","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"600","DOI":"10.1007\/978-3-031-28241-6_69","volume-title":"Advances in Information Retrieval","author":"\u0160 \u0160imsa","year":"2023","unstructured":"\u0160imsa, \u0160, \u0160ulc, M., Skalick\u00fd, M., Patel, Y., Hamdi, A.: DocILE 2023 teaser: document information localization and extraction. In: Kamps, J., et al. (eds.) ECIR 2023. LNCS, vol. 13982, pp. 600\u2013608. Springer, Cham (2023). https:\/\/doi.org\/10.1007\/978-3-031-28241-6_69"},{"doi-asserted-by":"crossref","unstructured":"\u0160imsa, \u0160., et al.: DocILE benchmark for document information localization and extraction. arXiv preprint arXiv:2302.05658 (2023). Accepted to ICDAR 2023","key":"21_CR22","DOI":"10.1007\/978-3-031-41679-8_9"},{"key":"21_CR23","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"105","DOI":"10.1007\/978-3-031-13643-6_8","volume-title":"Experimental IR Meets Multilinguality, Multimodality, and Interaction","author":"M Skalick\u00fd","year":"2022","unstructured":"Skalick\u00fd, M., \u0160imsa, \u0160, U\u0159i\u010d\u00e1\u0159, M., \u0160ulc, M.: Business document information extraction: Towards practical benchmarks. In: Barr\u00f3n-Cede\u00f1o, A., et al. (eds.) CLEF 2022. LNCS, vol. 13390, pp. 105\u2013117. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-13643-6_8"},{"unstructured":"Straka, J., Gruber, I.: Object detection pipeline using YOLOv8 for document information extraction. In: Aliannejadi, M., Faggioli, G., Ferro, N., Vlachos, M. (eds.) Working Notes of CLEF 2023 - Conference and Labs of the Evaluation Forum, Thessaloniki, Greece, 18\u201321 September. CEUR Workshop Proceedings, CEUR-WS.org (2023)","key":"21_CR24"},{"doi-asserted-by":"crossref","unstructured":"Tanaka, R., Nishida, K., Yoshida, S.: VisualMRC: machine reading comprehension on document images. In: AAAI (2021)","key":"21_CR25","DOI":"10.1609\/aaai.v35i15.17635"},{"doi-asserted-by":"crossref","unstructured":"Tang, Z., et al.: Unifying vision, text, and layout for universal document processing. arXiv (2022)","key":"21_CR26","DOI":"10.1109\/CVPR52729.2023.01845"},{"unstructured":"Tran, B.G., Bao, D.N.M., Bui, K.G., Duong, H.V., Nguyen, D.H., Nguyen, H.M.: Union-RoBERTa: RoBERTas ensemble technique for competition on document information localization and extraction. In: Aliannejadi, M., Faggioli, G., Ferro, N., Vlachos, M. (eds.) Working Notes of CLEF 2023 - Conference and Labs of the Evaluation Forum, Thessaloniki, Greece, 18\u201321 September. CEUR Workshop Proceedings, CEUR-WS.org (2023)","key":"21_CR27"},{"doi-asserted-by":"crossref","unstructured":"Wang, J., Jin, L., Ding, K.: LiLT: a simple yet effective language-independent layout transformer for structured document understanding. In: ACL (2022)","key":"21_CR28","DOI":"10.18653\/v1\/2022.acl-long.534"},{"unstructured":"Wang, Y., Du, J., Ma, J., Hu, P., Zhang, Z., Zhang, J.: USTC-iFLYTEK at DocILE: a multi-modal approach using domain-specific GraphDoc. In: Aliannejadi, M., Faggioli, G., Ferro, N., Vlachos, M. (eds.) Working Notes of CLEF 2023 - Conference and Labs of the Evaluation Forum, Thessaloniki, Greece, 18\u201321 September. CEUR Workshop Proceedings, CEUR-WS.org (2023)","key":"21_CR29"},{"unstructured":"Web: Industry Documents Library. https:\/\/www.industrydocuments.ucsf.edu\/. Accessed 20 Oct 2022","key":"21_CR30"},{"unstructured":"Web: Public Inspection Files. https:\/\/publicfiles.fcc.gov\/. Accessed 20 Oct 2022","key":"21_CR31"},{"doi-asserted-by":"crossref","unstructured":"Xu, Y., et al.: LayoutLMv2: multi-modal pre-training for visually-rich document understanding. In: ACL (2021)","key":"21_CR32","DOI":"10.18653\/v1\/2021.acl-long.201"},{"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: KDD (2020)","key":"21_CR33","DOI":"10.1145\/3394486.3403172"},{"doi-asserted-by":"crossref","unstructured":"Zhang, Z., Ma, J., Du, J., Wang, L., Zhang, J.: Multimodal pre-training based on graph attention network for document understanding. IEEE Trans. Multimed. (2022)","key":"21_CR34","DOI":"10.1109\/TMM.2022.3214102"},{"doi-asserted-by":"crossref","unstructured":"Zhong, X., Tang, J., Jimeno-Yepes, A.: PubLayNet: largest dataset ever for document layout analysis. In: ICDAR (2019)","key":"21_CR35","DOI":"10.1109\/ICDAR.2019.00166"},{"doi-asserted-by":"crossref","unstructured":"Zhou, J., Yu, H., Xie, C., Cai, H., Jiang, L.: iRMP: from printed forms to relational data model. In: HPCC (2016)","key":"21_CR36","DOI":"10.1109\/HPCC-SmartCity-DSS.2016.0199"},{"doi-asserted-by":"crossref","unstructured":"Zhu, Y., et al.: Aligning books and movies: towards story-like visual explanations by watching movies and reading books. In: ICCV (2015)","key":"21_CR37","DOI":"10.1109\/ICCV.2015.11"}],"container-title":["Lecture Notes in Computer Science","Experimental IR Meets Multilinguality, Multimodality, and Interaction"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-42448-9_21","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,12]],"date-time":"2024-03-12T16:25:49Z","timestamp":1710260749000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-42448-9_21"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031424472","9783031424489"],"references-count":37,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-42448-9_21","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":"11 September 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"CLEF","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference of the Cross-Language Evaluation Forum for European Languages","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Thessaloniki","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Greece","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":"18 September 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"21 September 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"14","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"clef2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/clef2023.clef-initiative.eu\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Single-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":"35","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":"10","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":"1","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":"29% - 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","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":"2","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":"7 Best of 2022 Labs + 13 Lab Overviews","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)"}}]}}