German FinBERT: A German Pre-trained Language Model

TL;DR

German FinBERT is a specialized pre-trained language model designed for financial text analysis in German, showing improved performance on finance-specific tasks compared to generic models.

Contribution

The paper introduces German FinBERT, a domain-specific pre-trained language model for German financial texts, trained on a large financial corpus for improved domain understanding.

Findings

Enhanced sentiment prediction accuracy on financial data

Better topic recognition in financial texts

Improved question answering performance in finance domain

Abstract

This study presents German FinBERT, a novel pre-trained German language model tailored for financial textual data. The model is trained through a comprehensive pre-training process, leveraging a substantial corpus comprising financial reports, ad-hoc announcements and news related to German companies. The corpus size is comparable to the data sets commonly used for training standard BERT models. I evaluate the performance of German FinBERT on downstream tasks, specifically sentiment prediction, topic recognition and question answering against generic German language models. My results demonstrate improved performance on finance-specific data, indicating the efficacy of German FinBERT in capturing domain-specific nuances. The presented findings suggest that German FinBERT holds promise as a valuable tool for financial text analysis, potentially benefiting various applications in the financial domain.