CopeNLU is a Natural Language Processing research group led by Isabelle Augenstein with a focus on researching methods for tasks that require a deep understanding of language, as opposed to shallow processing. We are affiliated with the Natural Language Processing Section at the Department of Computer Science, University of Copenhagen. We are interested in core methodology research on, among others, learning with limited training data and explainable AI; as well as applications thereof to tasks such as fact checking, gender bias detection and question answering. Our group is partly funded by a Sapere Aude Research Leader fellowship on `Learning to Explain Attitudes on Social Media’.
Learning with limited labelled data, including multi-task learning, weakly supervised and zero-shot learning
Determine the attitude expressed in a text towards a topic, and use this for automatic evidence-based fact checking
Explaining relationships between inputs and outputs of black-box machine learning models
Automatically detecting gendered language, and to what degree attitudes towards entities are influenced by gender bias
Training models to work well for multiple languages, including low-resource ones
Automatically processing scholarly data to assist researchers in finding publications, writing better papers, or tracking their impact.
Extract information about entities, phrases and relations between them from text to populate knowledge bases