معرفی
Katharina von der Wense is an Assistant Professor at the University of Colorado, currently on leave for Fall 2025. Her research focuses on Natural Language Processing (NLP), with a particular emphasis on low-resource languages and indigenous language documentation. She has contributed significantly to machine translation systems for underrepresented languages, ethical considerations in NLP, and educational technologies leveraging computational linguistics. Her work bridges technical innovation with sociocultural impact, addressing gaps in linguistic diversity and accessibility.
Her research explores topics such as morphological processing, cross-lingual transfer learning, and the application of large language models (LLMs) to real-world challenges. She actively participates in initiatives like the AmericasNLP workshop series, advancing NLP solutions for Indigenous languages of the Americas. Key areas include paradigm clustering, self-supervised learning for morphology, and the development of probing datasets for neural network analysis.
Her publications highlight interdisciplinary approaches, combining computational methods with linguistic theory to tackle challenges in education, cultural preservation, and algorithmic fairness. She has pioneered methodologies for evaluating LLM robustness, improving context handling in QA systems, and creating multilingual hate speech detection frameworks.
