Abstract
We address the problem of form understanding: finding text entities and the relationships/links between them in form images. The proposed FUDGE model formulates this problem on a graph of text elements (the vertices) and uses a Graph Convolutional Network to predict changes to the graph. The initial vertices are detected text lines and do not necessarily correspond to the final text entities, which can span multiple lines. Also, initial edges contain many false-positive relationships. FUDGE edits the graph structure by combining text segments (graph vertices) and pruning edges in an iterative fashion to obtain the final text entities and relationships. While recent work in this area has focused on leveraging large-scale pre-trained Language Models (LM), FUDGE achieves the same level of entity linking performance on the FUNSD dataset by learning only visual features from the (small) provided training set. FUDGE can be applied on forms where text recognition is difficult (e.g. degraded or historical forms) and on forms in resource-poor languages where pre-training such LMs is challenging. FUDGE is state-of-the-art on the historical NAF dataset.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Aggarwal, M., Gupta, H., Sarkar, M., Krishnamurthy, B.: Form2Seq : A framework for higher-order form structure extraction. In: Conference on Empirical Methods in Natural Language Processing (EMNLP) (2020)
Aggarwal, M., Sarkar, M., Gupta, H., Krishnamurthy, B.: Multi-modal association based grouping for form structure extraction. In: IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) (2020)
Battaglia, P., et al.: Relational inductive biases, deep learning, and graph networks. arXiv (2018). https://arxiv.org/pdf/1806.01261.pdf
Carbonell, M., Riba, P., Villegas, M., Fornés, A., Lladós, J.: Named entity recognition and relation extraction with graph neural networks in semi structured documents. In: 25th International Conference on Pattern Recognition (ICPR) (2020)
Davis, B., Morse, B., Cohen, S., Price, B., Tensmeyer, C.: Deep visual template-free form parsing. In: International Conference on Document Analysis and Recognition (ICDAR) (2019)
Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: BERT: Pre-training of deep bidirectional transformers for language understanding. In: Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT) (2019)
He, K., Gkioxari, G., Dollár, P., Girshick, R.: Mask R-CNN. In: International Conference on Computer Vision (ICCV), pp. 2961–2969 (2017)
Hong, T., Kim, D., Ji, M., Hwang, W., Nam, D., Park, S.: BROS: A pre-trained language model for understanding texts in document (2021). https://openreview.net/forum?id=punMXQEsPr0
Izmailov, P., Podoprikhin, D., Garipov, T., Vetrov, D., Wilson, A.: Averaging weights leads to wider optima and better generalization. In: 34th Conference on Uncertainty in Artificial Intelligence (UAI) (2018)
Jaume, G., Kemal Ekenel, H., Thiran, J.: FUNSD: a dataset for form understanding in noisy scanned documents. In: International Conference on Document Analysis and Recognition Workshops (ICDARW) (2019)
Loshchilov, I., Hutter, F.: Decoupled weight decay regularization. In: International Conference on Learning Representations (ICLR) (2019)
Palm, R.B., Laws, F., Winther, O.: Attend, copy, parse end-to-end information extraction from documents. In: International Conference on Document Analysis and Recognition (ICDAR) (2019)
Qasim, S.R., Mahmood, H., Shafait, F.: Rethinking table recognition using graph neural networks. In: International Conference on Document Analysis and Recognition (ICDAR) (2019)
Redmon, J., Farhadi, A.: YOLOv3: An incremental improvement. arXiv preprint arXiv:1804.02767 (2018)
Riba, P., Dutta, A., Goldmann, L., Fornés, A., Ramos, O., Lladós, J.: Table detection in invoice documents by graph neural networks. In: International Conference on Document Analysis and Recognition (ICDAR) (2019)
Sarkar, M., Aggarwal, M., Jain, A., Gupta, H., Krishnamurthy, B.: Document structure extraction using prior based high resolution hierarchical semantic segmentation. In: European Conference on Computer Vision (ECCV) (2020)
Vaswani, A., et al.: Attention is all you need. In: 31st Conference on Neural Information Processing Systems (NIPS) (2017)
Wang, Z., Zhan, M., Liu, X., Liang, D.: DocStruct: a multimodal method to extract hierarchy structure in document for general form understanding. In: Findings of the Association for Computational Linguistics: EMNLP (2020)
Wu, Y., He, K.: Group normalization. In: European Conference on Computer Vision (ECCV), pp. 3–19 (2018)
Xu, Y., et al.: LayoutLMv2: Multi-modal pre-training for visually-rich document understanding. In: 59th Annual Meeting of the Association for Computational Linguistics (ACL) (2021)
Xu, Y., Li, M., Cui, L., Huang, S., Wei, F., Zhou, M.: LayoutLM: pre-training of text and layout for document image understanding. In: International Conference on Knowledge Discovery & Data Mining (KDD) (2020)
Yang, X., Yumer, E., Asente, P., Kraley, M., Kifer, D., Lee Giles, C.: Learning to extract semantic structure from documents using multimodal fully convolutional neural networks. In: Conference on Computer Vision and Pattern Recognition (CVPR) (2017)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
Davis, B., Morse, B., Price, B., Tensmeyer, C., Wiginton, C. (2021). Visual FUDGE: Form Understanding via Dynamic Graph Editing. In: Lladós, J., Lopresti, D., Uchida, S. (eds) Document Analysis and Recognition – ICDAR 2021. ICDAR 2021. Lecture Notes in Computer Science(), vol 12821. Springer, Cham. https://doi.org/10.1007/978-3-030-86549-8_27
Download citation
DOI: https://doi.org/10.1007/978-3-030-86549-8_27
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-86548-1
Online ISBN: 978-3-030-86549-8
eBook Packages: Computer ScienceComputer Science (R0)