{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,25]],"date-time":"2025-03-25T15:25:43Z","timestamp":1742916343132,"version":"3.40.3"},"publisher-location":"Cham","reference-count":34,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031416811"},{"type":"electronic","value":"9783031416828"}],"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\/978-3-031-41682-8_14","type":"book-chapter","created":{"date-parts":[[2023,8,18]],"date-time":"2023-08-18T07:02:59Z","timestamp":1692342179000},"page":"216-230","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["A Character-Level Document Key Information Extraction Method with\u00a0Contrastive Learning"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-8590-2465","authenticated-orcid":false,"given":"Xinpeng","family":"Zhang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiyao","family":"Deng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Liangcai","family":"Gao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,8,19]]},"reference":[{"key":"14_CR1","doi-asserted-by":"crossref","unstructured":"Appalaraju, S., Jasani, B., Kota, B.U., Xie, Y., Manmatha, R.: DocFormer: end-to-end transformer for document understanding. In: 2021 IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 973\u2013983 (2021)","DOI":"10.1109\/ICCV48922.2021.00103"},{"key":"14_CR2","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":"14_CR3","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: BERT: Pre-training of deep bidirectional transformers for language understanding. In: Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers), pp. 4171\u20134186 (2019)"},{"key":"14_CR4","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"532","DOI":"10.1007\/978-3-030-86549-8_34","volume-title":"Document Analysis and Recognition \u2013 ICDAR 2021","author":"\u0141 Garncarek","year":"2021","unstructured":"Garncarek, \u0141, et al.: LAMBERT: layout-aware language modeling for information extraction. In: Llad\u00f3s, J., Lopresti, D., Uchida, S. (eds.) ICDAR 2021. LNCS, vol. 12821, pp. 532\u2013547. Springer, Cham (2021). https:\/\/doi.org\/10.1007\/978-3-030-86549-8_34"},{"key":"14_CR5","first-page":"39","volume":"34","author":"J Gu","year":"2021","unstructured":"Gu, J., et al.: Unidoc: unified pretraining framework for document understanding. Adv. Neural. Inf. Process. Syst. 34, 39\u201350 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"issue":"8","key":"14_CR6","doi-asserted-by":"publisher","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","volume":"9","author":"S Hochreiter","year":"1997","unstructured":"Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9(8), 1735\u20131780 (1997)","journal-title":"Neural Comput."},{"key":"14_CR7","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: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 36, pp. 10767\u201310775 (2022)","DOI":"10.1609\/aaai.v36i10.21322"},{"key":"14_CR8","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: Proceedings of the 30th ACM International Conference on Multimedia, pp. 4083\u20134091 (2022)","DOI":"10.1145\/3503161.3548112"},{"key":"14_CR9","doi-asserted-by":"crossref","unstructured":"Huang, Z., et al.: ICDAR 2019 competition on scanned receipt OCR and information extraction. In: 2019 International Conference on Document Analysis and Recognition (ICDAR), pp. 1516\u20131520 (2019)","DOI":"10.1109\/ICDAR.2019.00244"},{"key":"14_CR10","unstructured":"Huang, Z., Xu, W., Yu, K.: Bidirectional LSTM-CRF models for sequence tagging. arXiv preprint arXiv:1508.01991 (2015)"},{"key":"14_CR11","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: Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021, pp. 330\u2013343 (2021)","DOI":"10.18653\/v1\/2021.findings-acl.28"},{"key":"14_CR12","doi-asserted-by":"crossref","unstructured":"Jaume, G., Ekenel, H.K., Thiran, J.P.: FUNSD: a dataset for form understanding in noisy scanned documents. In: 2019 International Conference on Document Analysis and Recognition Workshops (ICDARW), vol. 2, pp. 1\u20136. IEEE (2019)","DOI":"10.1109\/ICDARW.2019.10029"},{"key":"14_CR13","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 the 2018 Conference on Empirical Methods in Natural Language Processing, pp. 4459\u20134469 (2018)","DOI":"10.18653\/v1\/D18-1476"},{"key":"14_CR14","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"389","DOI":"10.1007\/978-3-030-86159-9_28","volume-title":"Document Analysis and Recognition \u2013 ICDAR 2021 Workshops","author":"M Kerroumi","year":"2021","unstructured":"Kerroumi, M., Sayem, O., Shabou, A.: VisualWordGrid: information extraction from scanned documents using a multimodal approach. In: Barney Smith, E.H., Pal, U. (eds.) ICDAR 2021. LNCS, vol. 12917, pp. 389\u2013402. Springer, Cham (2021). https:\/\/doi.org\/10.1007\/978-3-030-86159-9_28"},{"key":"14_CR15","doi-asserted-by":"crossref","unstructured":"Kim, Y., Jernite, Y., Sontag, D., Rush, A.M.: Character-aware neural language models. In: Proceedings of the Thirtieth AAAI Conference on Artificial Intelligence, pp. 2741\u20132749 (2016)","DOI":"10.1609\/aaai.v30i1.10362"},{"key":"14_CR16","unstructured":"Lafferty, J., Mccallum, A., Pereira, F.: Conditional random fields: probabilistic models for segmenting and labeling sequence data. In: Proceedings of the Eighteenth International Conference on Machine Learning (ICML 2001), pp. 282\u2013289 (2002)"},{"key":"14_CR17","doi-asserted-by":"crossref","unstructured":"Li, Y., et al.: StrucTexT: structured text understanding with multi-modal transformers. In: Proceedings of the 29th ACM International Conference on Multimedia, pp. 1912\u20131920 (2021)","DOI":"10.1145\/3474085.3475345"},{"key":"14_CR18","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Doll\u00e1r, P., Girshick, R., He, K., Hariharan, B., Belongie, S.: Feature pyramid networks for object detection. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 936\u2013944 (2017)","DOI":"10.1109\/CVPR.2017.106"},{"key":"14_CR19","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 - 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":"14_CR20","doi-asserted-by":"crossref","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, Volume 2 (Industry Papers), pp. 32\u201339. Association for Computational Linguistics (2019)","DOI":"10.18653\/v1\/N19-2005"},{"key":"14_CR21","unstructured":"Liu, Y., et al.: RoBERTa: a robustly optimized BERT pretraining approach. arXiv preprint arXiv:1907.11692 (2019)"},{"key":"14_CR22","doi-asserted-by":"crossref","unstructured":"Mikolov, T., Karafi\u00e1t, M., Burget, L., Cernock\u00fd, J., Khudanpur, S.: Recurrent neural network based language model. In: INTERSPEECH 2010, 11th Annual Conference of the International Speech Communication Association, pp. 1045\u20131048. ISCA (2010)","DOI":"10.21437\/Interspeech.2010-343"},{"key":"14_CR23","unstructured":"Park, S., et al.: CORD: a consolidated receipt dataset for post-OCR parsing. In: Workshop on Document Intelligence at NeurIPS 2019 (2019)"},{"key":"14_CR24","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":"14_CR25","unstructured":"Radford, A., Narasimhan, K., Salimans, T., Sutskever, I., et al.: Improving language understanding by generative pre-training. https:\/\/ww.nasa.gov\/nh\/pluto-the-other-red-planet (2018)"},{"key":"14_CR26","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"564","DOI":"10.1007\/978-3-030-86549-8_36","volume-title":"Document Analysis and Recognition \u2013 ICDAR 2021","author":"T Stanis\u0142awek","year":"2021","unstructured":"Stanis\u0142awek, T., et al.: Kleister: key information extraction datasets involving long documents with complex layouts. In: Llad\u00f3s, J., Lopresti, D., Uchida, S. (eds.) ICDAR 2021. LNCS, vol. 12821, pp. 564\u2013579. Springer, Cham (2021). https:\/\/doi.org\/10.1007\/978-3-030-86549-8_36"},{"key":"14_CR27","doi-asserted-by":"crossref","unstructured":"Tang, G., et al.: MatchVIE: exploiting match relevancy between entities for visual information extraction. In: Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence, IJCAI-21, pp. 1039\u20131045. International Joint Conferences on Artificial Intelligence Organization (2021)","DOI":"10.24963\/ijcai.2021\/144"},{"key":"14_CR28","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems, vol. 30, pp. 5998\u20136008 (2017)"},{"key":"14_CR29","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: Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 7747\u20137757 (2022)","DOI":"10.18653\/v1\/2022.acl-long.534"},{"key":"14_CR30","doi-asserted-by":"crossref","unstructured":"Wang, J., et al.: Towards robust visual information extraction in real world: new dataset and novel solution. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 35, pp. 2738\u20132745 (2021)","DOI":"10.1609\/aaai.v35i4.16378"},{"key":"14_CR31","doi-asserted-by":"crossref","unstructured":"Xu, Y., et al.: LayoutLMv2: multi-modal pre-training for visually-rich document 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. 2579\u20132591 (2021)","DOI":"10.18653\/v1\/2021.acl-long.201"},{"key":"14_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":"14_CR33","doi-asserted-by":"crossref","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. IEEE (2021)","DOI":"10.1109\/ICPR48806.2021.9412927"},{"key":"14_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, pp. 1413\u20131422 (2020)","DOI":"10.1145\/3394171.3413900"}],"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\/978-3-031-41682-8_14","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,18]],"date-time":"2023-08-18T07:19:22Z","timestamp":1692343162000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-41682-8_14"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031416811","9783031416828"],"references-count":34,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-41682-8_14","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)"}}]}}