Abstract
Visually rich document understanding techniques have numerous practical application scenarios in the real world. However, existing researches tend to focus on large-scale models, especially pre-trained ones, training which is resource-consuming. Additionally, these models are unfeasible for low-resource situations, like edge applications. This paper proposes the LayoutGCN, a novel, lightweight architecture, to classify, extract, and structuralize information from visually rich documents. It treats a document as a graph of text blocks and employs convolution neural networks to encode all features from different modalities. Rich representations for text blocks containing textual, layout, and visual information are generated by a graph convolution network whose adjacency matrix is carefully designed to fully use the relative position information between text blocks. Extensive experiments on five benchmarks show the applicability of LayoutGCN for various downstream tasks and its comparable performance to existing large-scale models.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Appalaraju, S., Jasani, B., Kota, B.U., Xie, Y., Manmatha, R.: Docformer: end-to-end transformer for document understanding. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 993–1003 (2021)
Ba, J.L., Kiros, J.R., Hinton, G.E.: Layer normalization. arXiv preprint arXiv:1607.06450 (2016)
Cheng, Z., et al.: Trie++: towards end-to-end information extraction from visually rich documents. arXiv preprint arXiv:2207.06744 (2022)
Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: Bert: pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)
Garncarek, Ł, et al.: LAMBERT: layout-aware language modeling for information extraction. In: Lladós, J., Lopresti, D., Uchida, S. (eds.) ICDAR 2021. LNCS, vol. 12821, pp. 532–547. Springer, Cham (2021). https://doi.org/10.1007/978-3-030-86549-8_34
Ge, Z., Liu, S., Wang, F., Li, Z., Sun, J.: Yolox: exceeding yolo series in 2021. arXiv preprint arXiv:2107.08430 (2021)
Gehring, J., Auli, M., Grangier, D., Yarats, D., Dauphin, Y.N.: Convolutional sequence to sequence learning. In: International Conference on Machine Learning, pp. 1243–1252. PMLR (2017)
Gu, J., et al.: Unidoc: unified pretraining framework for document understanding. Adv. Neural Inf. Process. Syst. 34, 39–50 (2021)
Gu, Z., et al.: Xylayoutlm: towards layout-aware multimodal networks for visually-rich document understanding. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 4583–4592 (2022)
Guo, H., Qin, X., Liu, J., Han, J., Liu, J., Ding, E.: Eaten: entity-aware attention for single shot visual text extraction. In: 2019 International Conference on Document Analysis and Recognition (ICDAR), pp. 254–259. IEEE (2019)
Harley, A.W., Ufkes, A., Derpanis, K.G.: Evaluation of deep convolutional nets for document image classification and retrieval (2015)
He, K., Gkioxari, G., Dollár, P., Girshick, R.: Mask r-cnn. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2961–2969 (2017)
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. 10767–10775 (2022)
Huang, Y., Lv, T., Cui, L., Lu, Y., Wei, F.: Layoutlmv3: pre-training for document AI with unified text and image masking. arXiv preprint arXiv:2204.08387 (2022)
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. 1516–1520. IEEE (2019)
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) (2019)
Kim, Y.: Convolutional neural networks for sentence classification. arXiv preprint arXiv:1408.5882v2 (2014)
Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)
Lafferty, J., McCallum, A., Pereira, F.C.: Conditional random fields: probabilistic models for segmenting and labeling sequence data (2001)
Li, C., et al.: Structurallm: structural pre-training for form understanding. arXiv preprint arXiv:2105.11210 (2021)
Li, P., et al.: selfdoc: self-supervised document representation learning. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 5652–5660 (2021)
Li, Y., et al.: Structext: structured text understanding with multi-modal transformers. In: Proceedings of the 29th ACM International Conference on Multimedia, pp. 1912–1920 (2021)
Liu, X., Gao, F., Zhang, Q., Zhao, H.: Graph convolution for multimodal information extraction from visually rich documents. arXiv preprint arXiv:1903.11279 (2019)
Liu, Y., et al.: Roberta: a robustly optimized bert pretraining approach. arXiv preprint arXiv:1907.11692 (2019)
Park, S., et al.: Cord: a consolidated receipt dataset for post-ocr parsing. In: Workshop on Document Intelligence at NeurIPS 2019 (2019)
Powalski, R., Borchmann, Ł, Jurkiewicz, D., Dwojak, T., Pietruszka, M., Pałka, G.: Going full-TILT boogie on document understanding with text-image-layout transformer. In: Lladós, J., Lopresti, D., Uchida, S. (eds.) ICDAR 2021. LNCS, vol. 12822, pp. 732–747. Springer, Cham (2021). https://doi.org/10.1007/978-3-030-86331-9_47
Srivastava, N., Hinton, G., Krizhevsky, A., Sutskever, I., Salakhutdinov, R.: Dropout: a simple way to prevent neural networks from overfitting. J. Mach. Learn. Res. 15(1), 1929–1958 (2014)
Strubell, E., Ganesh, A., McCallum, A.: Energy and policy considerations for deep learning in nlp. arXiv preprint arXiv:1906.02243 (2019)
Wang, Z., Zhan, M., Liu, X., Liang, D.: Docstruct: a multimodal method to extract hierarchy structure in document for general form understanding. arXiv preprint arXiv:2010.11685 (2020)
Welling, M., Kipf, T.N.: Semi-supervised classification with graph convolutional networks. In: J. International Conference on Learning Representations (ICLR 2017) (2016)
Xu, Y., et al.: Layoutlmv2: multi-modal pre-training for visually-rich document understanding. arXiv preprint arXiv:2012.14740 (2022)
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. 1192–1200 (2020)
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. 4363–4370. IEEE (2021)
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. 1413–1422 (2020)
Acknowledgements
This research work is sponsored by Ant Group Security and Risk Management Fund.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Shi, D., Liu, S., Du, J., Zhu, H. (2023). LayoutGCN: A Lightweight Architecture for Visually Rich Document Understanding. In: Fink, G.A., Jain, R., Kise, K., Zanibbi, R. (eds) Document Analysis and Recognition - ICDAR 2023. ICDAR 2023. Lecture Notes in Computer Science, vol 14189. Springer, Cham. https://doi.org/10.1007/978-3-031-41682-8_10
Download citation
DOI: https://doi.org/10.1007/978-3-031-41682-8_10
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-41681-1
Online ISBN: 978-3-031-41682-8
eBook Packages: Computer ScienceComputer Science (R0)