NLP Researcher and Data Scientist
I'm an NLP Researcher at the University of Konstanz and a Software Engineer, specializing in large language models and all things data science!
A Python package for detecting intertextual links in Latin literature using pre-trained language models. The pipeline generates and reranks candidates to map sentences between source and query documents, with a focus on evaluating semantic and stylistic reuse.
We explore the application of large language models for topic classification within a low-resource German web environment, leveraging a dataset comprising millions of scraped webpages aimed at evaluating policy impacts.
A dedicated tool for systematic web page annotations, designed to streamline the process of annotating and analyzing web content for research and data science applications.
This project introduces a framework for robust, unified psychometric testing of language models, enabling comprehensive evaluation of their cognitive and linguistic capabilities.
We explore narratives and their patterns of influence by compiling a large dataset of news articles. Using large language models to annotate narratives as triples of hero, villain, and victim mentions, we track shared narratives and identify patterns of influence across partisanships.
ECCE helps you to analyze your documents and corpora by detecting named entities to extracting an entity network.
RAG pipeline for querying technical docs, with query expansion, HyDE, and a Gradio chat interface.
Fine-tuned RoBERTa for multilingual NER to make cross-lingual entity extraction easier.
A solarized VSCode theme with just the right contrast to keep your eyes comfy!