I am a Computational Linguist and Data Scientist at the University of Cologne, affiliated with the Data Center for the Humanities (DCH). I am building the Experimental Service Hub for the linguistics labs of the Faculty of Arts and Humanities, including the XLinC Lab and the Phonetics Lab. My work covers programming experiments (audio/video, reaction time, eye-tracking, EEG), developing data analysis pipelines, research data management and archiving, and offering consultation and training for researchers.

From 2024 to 2026, I was a Data Scientist at trivago N.V. in Düsseldorf. There I built rule-based, ML, and LLM models for matching, deduplication, and data enrichment, and developed BigQuery SQL and Python pipelines at scale.

From 2015 to 2024, I worked at the University of Cologne in the SFB 1252 “Prominence in Language”, mainly in the infrastructure project INF. I developed data pipelines and metadata schemas, supported corpus annotation and research data management, and trained and advised researchers across the collaborative research centre.

I completed my Ph.D. in Linguistics at the University of Cologne (2017–2022), supervised by Prof. Dr. Nikolaus P. Himmelmann and Prof. Dr. Kees van Deemter. My dissertation, Referring Expression Generation in Context, combined linguistic and computational approaches to how people choose referring expressions in discourse. Before that, I completed the Research Master’s in Linguistics at Utrecht University (2012–2014).

My interests include Natural Language Generation, the human evaluation of NLG systems, experimental linguistics, research data management, and building tools that make research data easier to explore and reuse.