Abstract
Information extraction (IE) from forms remains an unsolved problem, with some exceptions, like bills. Forms are complex and the templates are often unstable, due to the injection of advertising, extra conditions, or document merging. Our scenario deals with insurance forms used by brokers in Switzerland. Here, each combination of insurer, insurance type and language results in a new document layout, leading to a few hundred document types. To help brokers extract data from policies, we developed a new labeling method, called FLIE (form labeling for information extraction). FLIE first assigns a document to a cluster, grouping by language, insurer, and insurance type. It then labels the layout. To produce training data, the user annotates a sample document by hand, adding attribute names, i.e. provides a mapping. FLIE applies machine learning to propagate the mapping and extracts information. Our results are based on 24 Swiss policies in German: UVG (mandatory accident insurance), KTG (sick pay insurance), and UVGZ (optional accident insurance). Our solution has an accuracy of around 84–89%. It is currently being extended to other policy types and languages.
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
IG B2B for Insurers + Brokers (2020)
Swiss Financial Market Supervisory Authority FINMA (2020)
Adelfio, M.D., Samet, H.: Schema extraction for tabular data on the web. Proc. VLDB 6(6), 421–432 (2013)
Albon, C.: Machine learning with Python cookbook: practical solutions from preprocessing to deep learning, first edition. O’Reilly, Sebastopol (2018)
Balakrishnan, S., Halevy, A.Y., Harb, B., Lee, H., Madhavan, J., Rostamizadeh, A., Shen, W., Wilder, K., Wu, F., Yu, C.: Applying web tables in practice. In: CIDR 2015 (2015)
Bentley, J.L.: A Survey of Techniques for Fixed Radius Near Neighbor Searching. Technical report, 8 (1975)
Bommarito, I.I., Michael, J., Katz, D.M., Detterman, E.M.: LexNLP: natural language processing and information extraction for legal and regulatory texts. arXiv preprint arXiv:1806.03688 (2018)
Cowie, J.R., Lehnert, W.G.: Information extraction. Commun. ACM 39(1), 80–91 (1996)
Danilak, M.M.: Langdetect - Python port of Google’s language-detection (2016)
Gatterbauer, W., Bohunsky, P., Herzog, M., Krüpl, B., Pollak, B.: Towards domain-independent information extraction from web tables. In: Proceedings of the 16th International Conference on World Wide Web, pp. 71–80 (2007)
Glozman, R.: Chisel AI (2020)
Manning, C.D., Raghavan, P., Schütze, H.: Introduction to Information Retrieval. Cambridge University Press, Cambridge (2008)
Marano, P., Noussia, K. (eds.): InsurTech: A Legal and Regulatory View. Springer (2020)
Matthews, B.W.: Comparison of the predicted and observed secondary structure of T4 phage lysozyme. Biochim Biophys Acta 405(2), 442–451 (1975)
Nakatani, S.: Language Detection Library for Java (2010)
Nasar, Z., Jaffry, S.W., Malik, M.K.: Information extraction from scientific articles: a survey. Scientometrics 117(3), 1931–1990 (2018)
Pustulka, E., Hanne, T.: Text mining innovation for business. In: Dornberger, R. (eds.) New Trends in Business Information Systems and Technology. Studies in Systems, Decision and Control, vol. 294. Springer, Cham (2021). https://doi.org/10.1007/978-3-030-48332-6_4
Rogers, S., Girolami, M.A.: A First Course in Machine Learning. CRC Press, Chapman and Hall/CRC machine learning and pattern recognition series (2011)
Rousseeuw, P.J.: Silhouettes: a graphical aid to the interpretation and validation of cluster analysis. J. Comput. Appl. Math. 20, 53–65 (1987)
Sarawagi, S.: Information extraction. Found. Trends Databases 1(3), 261–377 (2008)
Shinyama, Y., Guglielmetti, P.: PDFMiner.six - Python PDF Parser (2020)
Sinha, A., Bayer, J., Bukhari, S.S.: Table localization and field value extraction in piping and instrumentation diagram images. In: 2019 International Conference on Document Analysis and Recognition Workshops (ICDARW), vol. 1, pp. 26–31. IEEE (2019)
Tereszkiewicz, P.: Digitalisation of insurance contract law: preliminary thoughts with special regard to insurer’s duty to advise. In: InsurTech: A Legal and Regulatory View, pp. 127–146. Springer (2020)
Acknowledgments
We gratefully acknowledge funding from the Innosuisse, www.innosuisse.ch, grant no 34604.1 IP-ICT, and from the FHNW.
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
Pustulka, E., Hanne, T., Gachnang, P., Biafora, P. (2021). FLIE: Form Labeling for Information Extraction. In: Arai, K., Kapoor, S., Bhatia, R. (eds) Proceedings of the Future Technologies Conference (FTC) 2020, Volume 2 . FTC 2020. Advances in Intelligent Systems and Computing, vol 1289. Springer, Cham. https://doi.org/10.1007/978-3-030-63089-8_35
Download citation
DOI: https://doi.org/10.1007/978-3-030-63089-8_35
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-63088-1
Online ISBN: 978-3-030-63089-8
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)