{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,9]],"date-time":"2025-09-09T22:29:59Z","timestamp":1757456999817,"version":"3.40.3"},"publisher-location":"Cham","reference-count":35,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031407727"},{"type":"electronic","value":"9783031407734"}],"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\/978-3-031-40773-4_2","type":"book-chapter","created":{"date-parts":[[2023,8,19]],"date-time":"2023-08-19T11:02:16Z","timestamp":1692442936000},"page":"25-39","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Enhancing GNN Feature Modeling for\u00a0Document Information Extraction Using Transformers"],"prefix":"10.1007","author":[{"given":"Mouad","family":"Hamri","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Maxime","family":"Devanne","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jonathan","family":"Weber","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Michel","family":"Hassenforder","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,8,20]]},"reference":[{"issue":"11","key":"2_CR1","doi-asserted-by":"publisher","first-page":"1162","DOI":"10.1109\/34.244677","volume":"15","author":"L O\u2019Gorman","year":"1993","unstructured":"O\u2019Gorman, L.: The document spectrum for page layout analysis. IEEE Trans. Pattern Anal. Mach. Intell. 15(11), 1162\u20131173 (1993). https:\/\/doi.org\/10.1109\/34.244677","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"2_CR2","doi-asserted-by":"crossref","unstructured":"LeCun, Y., et al.: Gradient-based learning applied to document recognition. Proc. IEEE 86(11), 2278\u20132324 (1998)","DOI":"10.1109\/5.726791"},{"key":"2_CR3","volume-title":"Neural Networks: A Comprehensive Foundation","author":"S Haykin","year":"1994","unstructured":"Haykin, S.: Neural Networks: A Comprehensive Foundation. Prentice Hall PTR, Upper Saddle River (1994)"},{"key":"2_CR4","unstructured":"Vaswani, A., et al. Attention is all you need (2017). arXiv:1706.03762 [cs]"},{"key":"2_CR5","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding (2019). arXiv:1810.04805 [cs]"},{"key":"2_CR6","unstructured":"Liu, Y., et al.: RoBERTa: a robustly optimized BERT pretraining approach (2019). arXiv:1907.11692 [Cs]"},{"key":"2_CR7","doi-asserted-by":"publisher","unstructured":"Ha, J., Phillips, I.T., Haralick, R.M.: Document page decomposition using bounding boxes of connected components of black pixels. In: Document Recognition II, vol. 2422, pp. 140\u2013151. International Society for Optics and Photonics (1995). https:\/\/doi.org\/10.1117\/12.205816","DOI":"10.1117\/12.205816"},{"key":"2_CR8","unstructured":"Socher, R., Bengio, Y., Manning , C.D.: Deep learning for NLP (without magic). In: Tutorial Abstracts of ACL 2012, ACL 2012, vol. 5. Association for Computational Linguistics (2012)"},{"key":"2_CR9","doi-asserted-by":"publisher","unstructured":"Palm, R.B., Laws, F., Winther, O.: Attend, copy, parse end-to-end information extraction from documents. In: 2019 International Conference on Document Analysis and Recognition (ICDAR), pp. 329\u2013336 (2019). https:\/\/doi.org\/10.1109\/ICDAR.2019.00060","DOI":"10.1109\/ICDAR.2019.00060"},{"key":"2_CR10","doi-asserted-by":"publisher","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: Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pp. 6495\u20136504. Association for Computational Linguistics (2020). https:\/\/doi.org\/10.18653\/v1\/2020.acl-main.580. https:\/\/www.aclweb.org\/anthology\/2020.acl-main.580)","DOI":"10.18653\/v1\/2020.acl-main.580"},{"key":"2_CR11","unstructured":"Patel, S., Bhatt, D.: Abstractive information extraction from scanned invoices (AIESI) using end-to-end sequential approach (2020). arXiv:2009.05728"},{"key":"2_CR12","doi-asserted-by":"crossref","unstructured":"Katti, A.R., Reisswig, C., Guder, C., Brarda, S., Bickel, S., H\u00f6hne, J., Faddoul, J.B.: Chargrid: towards understanding 2D documents. In: Proceedings of EMNLP, pp. 4459\u20134469 (2018)","DOI":"10.18653\/v1\/D18-1476"},{"key":"2_CR13","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":"2_CR14","doi-asserted-by":"crossref","unstructured":"Davis, B., Morse, B., Cohen, S., Price, B., Tensmeyer, C.: Deep visual template-free form parsing. In: ICDAR, pp. 134\u2013141 (2019)","DOI":"10.1109\/ICDAR.2019.00030"},{"key":"2_CR15","doi-asserted-by":"publisher","unstructured":"Liu, X., Gao, F., Zhang, Q., Zhao, H.: Graph convolution for multimodal information extraction from visually rich documents. In: Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, vol. 2 (Industry Papers), pp. 32\u201339. Association for Computational Linguistics, Minneapolis . https:\/\/doi.org\/10.18653\/v1\/N19-2005","DOI":"10.18653\/v1\/N19-2005"},{"key":"2_CR16","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 and Data Mining (2020)","DOI":"10.1145\/3394486.3403172"},{"key":"2_CR17","unstructured":"Xu, Y., et al.: LayoutLMv2: multi-modal pre-training for visually-rich document understanding (2011). arXiv:2012.14740 [cs]"},{"key":"2_CR18","unstructured":"Kipf, T.N., Welling, M.: Semi-supervised classification with graph convolutional networks (2017). arXiv:1609.02907 [cs, stat]"},{"key":"2_CR19","unstructured":"Hamilton, W.L., Ying, R., Leskovec, J.: Inductive representation learning on large graphs (2018). arXiv:1706.02216 [cs, stat]"},{"key":"2_CR20","unstructured":"Veli\u010dkovi\u0107, P., Cucurull, G., Casanova, A., Romero, A., Li\u00f2, P., Bengio, Y.: graph attention networks (2018). arXiv:1710.10903 [cs, stat]"},{"key":"2_CR21","doi-asserted-by":"crossref","unstructured":"Shi, Y., Huang, Z., Feng, S., Zhong, H., Wang, W., Sun, Y.: Masked label prediction: unified message passing model for semi-supervised classification (2021). arXiv:2009.03509 [cs, stat]","DOI":"10.24963\/ijcai.2021\/214"},{"key":"2_CR22","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. In: Proceedings of the 28th International Conference on Neural Information Processing Systems (NIPS 2015), vol. 1, pp. 91\u201399. MIT Press, Cambridge (2015)"},{"key":"2_CR23","doi-asserted-by":"publisher","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: 2019 International Conference on Document Analysis and Recognition (ICDAR), pp. 122\u2013127 (2019). https:\/\/doi.org\/10.1109\/ICDAR.2019.00028","DOI":"10.1109\/ICDAR.2019.00028"},{"key":"2_CR24","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"},{"key":"2_CR25","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"854","DOI":"10.1007\/978-3-030-86331-9_55","volume-title":"Document Analysis and Recognition \u2013 ICDAR 2021","author":"D Belhadj","year":"2021","unstructured":"Belhadj, D., Bela\u00efd, Y., Bela\u00efd, A.: Consideration of the word\u2019s neighborhood in GATs for information extraction in semi-structured documents. In: Llad\u00f3s, J., Lopresti, D., Uchida, S. (eds.) ICDAR 2021. LNCS, vol. 12822, pp. 854\u2013869. Springer, Cham (2021). https:\/\/doi.org\/10.1007\/978-3-030-86331-9_55"},{"key":"2_CR26","doi-asserted-by":"publisher","unstructured":"Huang, Z., et al.: ICDAR2019 competition on scanned receipt OCR and Information extraction. In: 2019 International Conference on Document Analysis and Recognition (ICDAR), pp. 1516\u20131520 (2019). https:\/\/doi.org\/10.1109\/ICDAR.2019.00244","DOI":"10.1109\/ICDAR.2019.00244"},{"key":"2_CR27","unstructured":"Defferrard, M., Bresson, X., Vandergheynst, P.: Convolutional neural networks on graphs with fast localized spectral filtering. In: Advances in Neural Information Processing Systems, pp. 3844\u20133852 (2016)"},{"key":"2_CR28","unstructured":"Velickovic, P., Cucurull, G., Casanova, A., Romero, A., Lio, A., Bengio, Y.: Graph attention networks. In: Proceedings of ICLR, pp. 1\u201312 (2017)"},{"key":"2_CR29","unstructured":"Heinzerling, B., Strube, M.: BPEmb: tokenization-free pre-trained subword embeddings in 275 languages. In: Proceedings of the 11th International Conference on Language Resources and Evaluation (2018)"},{"key":"2_CR30","unstructured":"Kipf, T.N., Welling, M.: Semi-supervised classification with graph convolutional networks. In: International Conference on Learning Representations (ICLR) (2017)"},{"key":"2_CR31","doi-asserted-by":"crossref","unstructured":"Li, Y., et al.: StrucTexT: structured text understanding with multi-modal transformers (2021). arXiv:2108.02923 [cs]","DOI":"10.1145\/3474085.3475345"},{"key":"2_CR32","doi-asserted-by":"crossref","unstructured":"Li, M., et al.: DocBank: a benchmark dataset for document layout analysis (2020). arXiv:2006.01038 [cs]","DOI":"10.18653\/v1\/2020.coling-main.82"},{"key":"2_CR33","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":"2_CR34","unstructured":"Yu, W., Lu, N., Qi, X., Gong, P., Xiao, R.: PICK: processing key information extraction from documents using improved graph learning-convolutional networks (2004). arXiv:2004.07464 [cs]"},{"key":"2_CR35","unstructured":"Tchoubith, N., Calusha, P.: ICDAR 2019 robust reading challenge on scanned receipts OCR and information extraction (2021). https:\/\/github.com\/BlackStar1313\/ICDAR-2019-RRC-SROIE"}],"container-title":["Lecture Notes in Computer Science","Reproducible Research in Pattern Recognition"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-40773-4_2","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,19]],"date-time":"2023-08-19T11:02:32Z","timestamp":1692442952000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-40773-4_2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031407727","9783031407734"],"references-count":35,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-40773-4_2","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":"20 August 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"RRPR","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Workshop on Reproducible Research in Pattern Recognition","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Montreal, QC","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Canada","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"21 August 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"21 August 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"rrpr2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/rrpr2022.sciencesconf.org\/","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":"9","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":"5","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":"4","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":"56% - 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":"2.8","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":"1.6","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":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}