Alexander Mehler

Predicting Topic (Co-)Occurrence Using Topic Networks Built from the Project Gutenberg Corpus

GhostWriter: Hidden AI-Generated Texts over Multiple Languages, Domains and Generators

Individual Text Corpora Predict User-Specific Knowledge: Benchmarks of Individualized Knowledge Simulation

This study examines whether individual text corpora from search histories can be used to simulate individual knowledge, and compared several large language models on this task, of which only Qwen3-1.7B proved viable.

Towards the Generation and Application of Dynamic Web-Based Visualization of UIMA-based Annotations for Big-Data Corpora with the Help of Unified Dynamic Annotation Visualizer

UDAV is a web-based solution that implements features not supported by comparable tools, enabling a customizable and extensible toolbox for interacting with annotations and allowing integration into existing big-data frameworks.