Cross-lingual German Biomedical Information Extraction: from Zero-shot to Human-in-the-Loop

TL;DR

This paper proposes a method for extracting biomedical information from German clinical texts using transfer and active learning, complemented by an interactive user interface for model inspection and annotation, aiming to improve performance with limited data.

Contribution

It introduces a novel combination of transfer learning, active learning, and an interactive interface for German biomedical information extraction with minimal annotations.

Findings

Effective transfer learning strategies for German biomedical texts.

Active learning reduces annotation effort.

Interactive interface enhances model inspection and annotation quality.

Abstract

This paper presents our project proposal for extracting biomedical information from German clinical narratives with limited amounts of annotations. We first describe the applied strategies in transfer learning and active learning for solving our problem. After that, we discuss the design of the user interface for both supplying model inspection and obtaining user annotations in the interactive environment.