Abstract
Information Extraction and Named Entity Recognition algorithms derive major applications related to many practical document analysis system. Semi structured documents pose several challenges when it comes to extract relevant information from these documents. The state-of-the-art methods heavily rely on feature engineering to perform layout-specific extraction of information and therefore do not generalize well. Extracting information without taking the document layout into consideration is required as a first step to develop a general solution to this problem. To address this challenge, we propose a deep learning based pipeline to extract information from documents. For this purpose, we define ‘information’ to be a set of entities that have a label and a corresponding value, e.g., application_number: ADNF8932NF and submission_date: 15FEB19. We form relational triplets by connecting one entity to another via a relationship, such as (max_temperature, is, 100 degrees) and train a neural tensor network that is well-suited for this kind of data to predict high confidence scores for true triplets. Up to 96% test accuracy on real world documents from publicly available GHEGA dataset demonstrate the effectiveness of our approach.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Bansal, T., Neelakantan, A., McCallum, A.: RelNet: end-to-end modeling of entities & relations. CoRR abs/1706.07179 (2017). http://arxiv.org/abs/1706.07179
Breuel, T.M.: The OCRopus open source OCR system. In: Document Recognition and Retrieval XV, vol. 6815, p. 68150F. International Society for Optics and Photonics (2008)
Cai, C.H., Ke, D., Xu, Y., Su, K.: Symbolic manipulation based on deep neural networks and its application to axiom discovery. In: 2017 International Joint Conference on Neural Networks (IJCNN), pp. 2136–2143. IEEE (2017)
Cesarini, F., Francesconi, E., Gori, M., Soda, G.: Analysis and understanding of multi-class invoices. Doc. Anal. Recogn. 6(2), 102–114 (2003). https://doi.org/10.1007/s10032-002-0084-6
Dengel, A.R.: Making documents work: challenges for document understanding. In: 7th International Conference on Document Analysis and Recognition, p. 1026. IEEE (2003)
Esser, D., Schuster, D., Muthmann, K., Berger, M., Schill, A.: Automatic indexing of scanned documents: a layout-based approach. In: Document Recognition and Retrieval XIX, vol. 8297, p. 82970H. International Society for Optics and Photonics (2012)
Liu, Q., et al.: Probabilistic reasoning via deep learning: neural association models. arXiv preprint arXiv:1603.07704 (2016)
Liu, Q., Jiang, H., Ling, Z.H., Zhu, X., Wei, S., Hu, Y.: Combing context and commonsense knowledge through neural networks for solving Winograd schema problems. In: AAAI Spring Symposium Series (2017)
López, G., Quesada, L., Guerrero, L.A.: Alexa vs. Siri vs. Cortana vs. Google Assistant: a comparison of speech-based natural user interfaces. In: Nunes, I. (ed.) AHFE 2017. Advances in Intelligent Systems and Computing, vol. 592, pp. 241–250. Springer, Cham (2017). https://doi.org/10.1007/978-3-319-60366-7_23
Medvet, E., Bartoli, A., Davanzo, G.: A probabilistic approach to printed document understanding. Int. J. Doc. Anal. Recogn. (IJDAR) 14(4), 335–347 (2011). https://doi.org/10.1007/s10032-010-0137-1
Nieze, A.: How to draw a Rubik’s cube in Inkscape, September 2014. http://goinkscape.com/how-to-draw-a-rubiks-cube-in-inkscape/
Rusinol, M., Benkhelfallah, T., Poulain d’Andecy, V.: Field extraction from administrative documents by incremental structural templates. In: 12th International Conference on Document Analysis and Recognition, pp. 1100–1104. IEEE (2013)
Schuster, D., et al.: Intellix-end-user trained information extraction for document archiving. In: 12th International Conference on Document Analysis and Recognition, pp. 101–105. IEEE (2013)
Shafait, F., Keysers, D., Breuel, T.M.: Efficient implementation of local adaptive thresholding techniques using integral images. In: Document recognition and retrieval XV, vol. 6815, p. 681510. International Society for Optics and Photonics (2008)
Socher, R., Chen, D., Manning, C.D., Ng, A.: Reasoning with neural tensor networks for knowledge base completion. In: Advances in Neural Information Processing Systems, pp. 926–934 (2013)
Sorio, E., Bartoli, A., Davanzo, G., Medvet, E.: A domain knowledge-based approach for automatic correction of printed invoices. In: International Conference on Information Society (i-Society 2012), pp. 151–155. IEEE (2012)
Strubell, E., Verga, P., Belanger, D., McCallum, A.: Fast and accurate sequence labeling with iterated dilated convolutions. CoRR abs/1702.02098 (2017). http://arxiv.org/abs/1702.02098
Trivedi, R., Dai, H., Wang, Y., Song, L.: Know-evolve: deep temporal reasoning for dynamic knowledge graphs. In: Proceedings of the 34th International Conference on Machine Learning, vol. 70, pp. 3462–3471. JMLR. org (2017)
Van Beusekom, J., Shafait, F., Breuel, T.M.: Combined orientation and skew detection using geometric text-line modeling. Int. J. Doc. Anal. Recogn. (IJDAR) 13(2), 79–92 (2010)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Shehzad, K., Ul-Hasan, A., Malik, M.I., Shafait, F. (2020). Named Entity Recognition in Semi Structured Documents Using Neural Tensor Networks. In: Bai, X., Karatzas, D., Lopresti, D. (eds) Document Analysis Systems. DAS 2020. Lecture Notes in Computer Science(), vol 12116. Springer, Cham. https://doi.org/10.1007/978-3-030-57058-3_28
Download citation
DOI: https://doi.org/10.1007/978-3-030-57058-3_28
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-57057-6
Online ISBN: 978-3-030-57058-3
eBook Packages: Computer ScienceComputer Science (R0)
