{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,9]],"date-time":"2025-09-09T21:00:40Z","timestamp":1757451640893,"version":"3.40.3"},"publisher-location":"Cham","reference-count":38,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031442223"},{"type":"electronic","value":"9783031442230"}],"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\/978-3-031-44223-0_32","type":"book-chapter","created":{"date-parts":[[2023,9,21]],"date-time":"2023-09-21T05:01:41Z","timestamp":1695272501000},"page":"394-406","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["GenTC: Generative Transformer via Contrastive Learning for Receipt Information Extraction"],"prefix":"10.1007","author":[{"given":"Xinrui","family":"Deng","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zheng","family":"Huang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kefan","family":"Ma","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kai","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jie","family":"Guo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Weidong","family":"Qiu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,9,22]]},"reference":[{"doi-asserted-by":"crossref","unstructured":"Aberdam, A., et al.: Sequence-to-sequence contrastive learning for text recognition. In: CVPR (2021)","key":"32_CR1","DOI":"10.1109\/CVPR46437.2021.01505"},{"doi-asserted-by":"crossref","unstructured":"Cao, H., et al.: GMN: generative multi-modal network for practical document information extraction. In: Proceedings of AACL (2022)","key":"32_CR2","DOI":"10.18653\/v1\/2022.naacl-main.276"},{"unstructured":"Chen, T., Kornblith, S., Norouzi, M., Hinton, G.E.: A simple framework for contrastive learning of visual representations. In: ICML (2020)","key":"32_CR3"},{"unstructured":"Denk, T.I., Reisswig, C.: BERTgrid: contextualized embedding for 2D document representation and understanding. CoRR (2019)","key":"32_CR4"},{"unstructured":"Devlin, J., Chang, M., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. In: Proceedings of AACL (2019)","key":"32_CR5"},{"doi-asserted-by":"crossref","unstructured":"Gao, T., Yao, X., Chen, D.: SimCSE: simple contrastive learning of sentence embeddings. In: EMNLP (1) (2021)","key":"32_CR6","DOI":"10.18653\/v1\/2021.emnlp-main.552"},{"doi-asserted-by":"crossref","unstructured":"He, K., Fan, H., Wu, Y., Xie, S., Girshick, R.B.: Momentum contrast for unsupervised visual representation learning. In: CVPR (2020)","key":"32_CR7","DOI":"10.1109\/CVPR42600.2020.00975"},{"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 AAAI (2022)","key":"32_CR8","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 Multimedia (2022)","key":"32_CR9","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":"32_CR10","DOI":"10.1109\/ICDAR.2019.00244"},{"doi-asserted-by":"crossref","unstructured":"Jiang, Z., Huang, Z., Lian, Y., Guo, J., Qiu, W.: Integrating coordinates with context for information extraction in document images. In: ICDAR (2019)","key":"32_CR11","DOI":"10.1109\/ICDAR.2019.00065"},{"unstructured":"Jiang, Z., Chen, T., Chen, T., Wang, Z.: Robust pre-training by adversarial contrastive learning. In: NeurIPS (2020)","key":"32_CR12"},{"doi-asserted-by":"crossref","unstructured":"Katti, A.R., et al.: CharGRID: towards understanding 2D documents. In: EMNLP (2018)","key":"32_CR13","DOI":"10.18653\/v1\/D18-1476"},{"key":"32_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":"32_CR15","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"498","DOI":"10.1007\/978-3-031-19815-1_29","volume-title":"Computer Vision - ECCV 2022, ECCV 2022","author":"G Kim","year":"2022","unstructured":"Kim, G., et al.: OCR-free document understanding transformer. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) Computer Vision - ECCV 2022, ECCV 2022. Lecture Notes in Computer Science, vol. 13688, pp. 498\u2013517. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-19815-1_29"},{"doi-asserted-by":"crossref","unstructured":"Lee, C., et al.: FormNet: structural encoding beyond sequential modeling in form document information extraction. In: ACL (1) (2022)","key":"32_CR16","DOI":"10.18653\/v1\/2022.acl-long.260"},{"unstructured":"Lee, K., et al.: Pix2struct: screenshot parsing as pretraining for visual language understanding. CoRR (2022)","key":"32_CR17"},{"unstructured":"Lee, S., Lee, D.B., Hwang, S.J.: Contrastive learning with adversarial perturbations for conditional text generation. In: ICLR (2021)","key":"32_CR18"},{"doi-asserted-by":"crossref","unstructured":"Lewis, M., et al.: BART: denoising sequence-to-sequence pre-training for natural language generation, translation, and comprehension. In: ACL (2020)","key":"32_CR19","DOI":"10.18653\/v1\/2020.acl-main.703"},{"doi-asserted-by":"crossref","unstructured":"Li, C., et al.: StructuralLM: structural pre-training for form understanding. In: ACL\/IJCNLP (1) (2021)","key":"32_CR20","DOI":"10.18653\/v1\/2021.acl-long.493"},{"unstructured":"Li, C., et al.: Pp-ocrv3: more attempts for the improvement of ultra lightweight OCR system. CoRR (2022)","key":"32_CR21"},{"key":"32_CR22","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"},{"doi-asserted-by":"crossref","unstructured":"Liu, Z., et al.: Swin transformer: hierarchical vision transformer using shifted windows. In: ICCV (2021)","key":"32_CR23","DOI":"10.1109\/ICCV48922.2021.00986"},{"unstructured":"Loshchilov, I., Hutter, F.: Decoupled weight decay regularization. In: ICLR (Poster) (2019)","key":"32_CR24"},{"unstructured":"van den Oord, A., Li, Y., Vinyals, O.: Representation learning with contrastive predictive coding. CoRR (2018)","key":"32_CR25"},{"unstructured":"Qian, Y., Santus, E., Jin, Z., Guo, J., Barzilay, R.: Graphie: a graph-based framework for information extraction. In: Proceedings of AACL (2019)","key":"32_CR26"},{"doi-asserted-by":"crossref","unstructured":"Schroff, F., Kalenichenko, D., Philbin, J.: FaceNet: a unified embedding for face recognition and clustering. In: CVPR (2015)","key":"32_CR27","DOI":"10.1109\/CVPR.2015.7298682"},{"unstructured":"Sohn, K.: Improved deep metric learning with multi-class n-pair loss objective. In: NIPS (2016)","key":"32_CR28"},{"unstructured":"Su, Y., Lan, T., Wang, Y., Yogatama, D., Kong, L., Collier, N.: A contrastive framework for neural text generation. CoRR (2022)","key":"32_CR29"},{"unstructured":"Teng, Z., Chen, C., Zhang, Y., Zhang, Y.: Contrastive latent variable models for neural text generation. In: UAI (2022)","key":"32_CR30"},{"unstructured":"Vaswani, A., et al.: Attention is all you need. In: NIPS (2017)","key":"32_CR31"},{"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 AAAI (2021)","key":"32_CR32","DOI":"10.1609\/aaai.v35i4.16378"},{"doi-asserted-by":"crossref","unstructured":"Xu, Y., et al.: Layoutlmv2: multi-modal pre-training for visually-rich document understanding. In: ACL\/IJCNLP (1) (2021)","key":"32_CR33","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: Proceedings of KDD (2020)","key":"32_CR34","DOI":"10.1145\/3394486.3403172"},{"unstructured":"Xu, Y., et al.: LayoutxLM: multimodal pre-training for multilingual visually-rich document understanding. CoRR (2021)","key":"32_CR35"},{"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: ICPR (2020)","key":"32_CR36"},{"doi-asserted-by":"crossref","unstructured":"Zhang, P., et al.: TRIE: end-to-end text reading and information extraction for document understanding. In: ACM Multimedia (2020)","key":"32_CR37","DOI":"10.1145\/3394171.3413900"},{"doi-asserted-by":"crossref","unstructured":"Zhang, S., Shen, Y., Tan, Z., Wu, Y., Lu, W.: De-bias for generative extraction in unified NER task. In: ACL (1) (2022)","key":"32_CR38","DOI":"10.18653\/v1\/2022.acl-long.59"}],"container-title":["Lecture Notes in Computer Science","Artificial Neural Networks and Machine Learning \u2013 ICANN 2023"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-44223-0_32","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,9,21]],"date-time":"2023-09-21T06:15:50Z","timestamp":1695276950000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-44223-0_32"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031442223","9783031442230"],"references-count":38,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-44223-0_32","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":"22 September 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICANN","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Artificial Neural Networks","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Heraklion","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":"26 September 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 September 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"32","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icann2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/e-nns.org\/icann2023\/","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":"easyacademia.org","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"947","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":"426","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":"22","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":"45% - 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":"2.4","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","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":"type of other papers accepted  : 9 Abstract","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)"}}]}}