Anonymization of German financial documents using neural network-based language models with contextual word representations
| Autor: | Robin Stenzel, Anna Ladi, Maren Pielka, Lars Patrick Hillebrand, Rajkumar Ramamurthy, David Biesner, Rafet Sifa, Christian Bauckhage, Rüdiger Loitz, Max Lübbering |
|---|---|
| Přispěvatelé: | Publica |
| Rok vydání: | 2021 |
| Předmět: |
Business process
Computer science computer.software_genre RNN sequence tagging anonymization Text processing Finance financial documents business.industry Applied Mathematics Deep learning transformers Computer Science Applications neural nets Management information systems Information extraction Information sensitivity Computational Theory and Mathematics restrict Modeling and Simulation Language model Artificial intelligence business computer BERT Information Systems |
| Zdroj: | International Journal of Data Science and Analytics. 13:151-161 |
| ISSN: | 2364-4168 2364-415X |
| DOI: | 10.1007/s41060-021-00285-x |
| Popis: | The automatization and digitalization of business processes have led to an increase in the need for efficient information extraction from business documents. However, financial and legal documents are often not utilized effectively by text processing or machine learning systems, partly due to the presence of sensitive information in these documents, which restrict their usage beyond authorized parties and purposes. To overcome this limitation, we develop an anonymization method for German financial and legal documents using state-of-the-art natural language processing methods based on recurrent neural nets and transformer architectures. We present a web-based application to anonymize financial documents and a large-scale evaluation of different deep learning techniques. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
Full text from SpringerLink