I work on natural language processing (including large language models) and machine learning. Specifically, I am interested in developing tools for low-resource languages and in moving the field away from focussing (nearly exclusively) on 'popular' languages such as English or Chinese. However, the lack of available datasets for such languages requires the development of new machine learning algorithms and models. Therefore, a lot of my research is centered around machine learning techniques aimed at overcoming data sparsity, such as, inter alia, transfer learning, domain adaptation, or meta-learning. In addition to my work on low-resource languages, I am also working on approaches for low-resource domains. Specifically, I am focussing on the domains of medicine and education.
keywords
natural language processing, machine learning, deep learning, transfer learning, multilingual natural language processing, large language models
