Marius Hamacher

Marius Hamacher, MSc Foto: Henrik Schipper

Marius Hamacher, MSc

Research assistant at the research professorship "Computational Linguistics" in the project KISTRA

Email: marius.hamacher

Phone: +49 2331 987 - 4899

Universitätsstraße 27 – PRG / Building 5
Raum B117 / 1. OG
58097 Hagen

What is my role within CATALPA?

As a researcher in Natural Language Processing (NLP), I am trying to future-proof NLP systems and make them robust against dynamically changing language.

Why CATALPA?

While humans understand and create language effortlessly, state of the art AI models lack this ability.
I hope to find ways to bridge this gap with the help of the colleagues in CATALPA, using the interdisciplinary environment to spark new ideas from unexpected angles to remedy this shortcoming.

    • Researcher at the Research Group for Computational Linguistics at the FernUni Hagen (seit 2022)
    • Researcher at the Language Technology Lab at the University of Duisburg-Essen (2020-2022)
    • Researcher for Project KISTRA (since 2020)
    • Study of Applied Cognitive and Media Science (B.Sc) at the University of Duisburg-Essen (2017-2020)
    • Research Assistant at the Language Technology Lab at the University of Duisburg-Essen (2017-2020)
    • Study of Applied Cognitive and Media Science (B.Sc) at the University of Duisburg-Essen (2013-2017)
    • Diachronic Language Modelling
    • Model Robustness
    • Explainable AI
  • I am working in the project "KISTRA: Einsatz von KI zur Früherkennung von Straftaten [Use of AI for early detection of crimes]" of the professorship "Computational Linguistics".

  • Workshop Article
    Aker, A., Hamacher, M., Nti, A., Smets, A., Gravenkamp, H., Erdmann, J., ... & Marchi, F. (2019). Corpus of News Articles Annotated with Article Level Sentiment. In NewsIR@ SIGIR (pp. 30-35).

    arXiv Preprint
    Zufall, F., Hamacher, M., Kloppenborg, K., & Zesch, T. (2020). A Legal Approach to Hate Speech: Operationalizing the EU's Legal Framework against the Expression of Hatred as an NLP Task. arXiv preprint https://arxiv.org/abs/2004.03422