Hier finden Sie wissenschaftliche Publikationen aus den Fraunhofer-Instituten.

Leveraging Contextual Text Representations for Anonymizing German Financial Documents

: Biesner, David; Ramamurthy, Rajkumar; Lübbering, Max; Fürst, Benedikt; Ismail, H.; Hillebrand, L.; Ladi, A.; Pielka, M.; Stenzel, R.; Khameneh, T.; Krapp, V.; Huseynov, I.; Schlums, J.; Stoll, U.; Warning, U.; Kliem, B.; Bauckhage, C.; Sifa, R.

Fulltext (PDF; )

Association for the Advancement of Artificial Intelligence -AAAI-:
AAAI-2020 Workshop on Knowledge Discovery from Unstructured Data in Financial Services. Accepted Papers. Online resource : February 7th, 2020, New York, NY, USA
Online im WWW, 2020
Paper 7, 6 pp.
Conference on Artificial Intelligence (AAAI) <34, 2020, New York/NY>
Workshop on Knowledge Discovery from Unstructured Data in Financial Services <2020, New York/NY>
Bundesministerium für Bildung und Forschung BMBF (Deutschland)
01-S18038A; ML2R
Conference Paper, Electronic Publication
Fraunhofer IAIS ()

Despite the high availability of financial and legal documents they are often not utilized by text processing or machine learning systems, even though the need for automated processing and extraction of useful patterns from these documents is increasing. This is partly due to the presence of sensitive entities in these documents, which restrict their usage beyond authorized parties and purposes. To overcome this limitation, we consider the task of anonymization in financial and legal documents using state-of-the-art natural language processing methods. Towards this, we present a web-based application to anonymize financial documents and also a largescale evaluation of different deep learning techniques.