7 CopeNLU papers are accepted to appear at EMNLP 2020, on fact checking, explainability, domain adaptation, and more.

2 papers by CopeNLU authors are accepted to appear at ACL 2020, on explainable fact checking, as as well as on script conversion.

4 papers by CopeNLU authors are to be presented at EMNLP 2019 and co-located events, on fact checking and disinformation, as well as on multi-task and multi-lingual learning.

2 papers by CopeNLU authors are accepted to appear at ACL 2019, on discovering probabilistic implications in typological knowledge bases as well as gendered language

3 papers by CopeNLU authors are accepted to appear at NAACL 2019. Topics span from population of typological knowledge bases and weak supervision from disparate lexica to frame detection in online fora.



Associate Professor

Isabelle’s main research interests are natural language understanding and learning with limited training data.

PhD Student

Pepa’s research interests are multilingual fact checking and question answering.

PhD Student

Andreas’ main research areas are representation learning and domain adaptation, with a focus on scientific texts.

PhD Student

Dustin’s research interests include fact checking and knowledge base population, with a focus on scientific texts.

PhD Student

Nils researches low-resource learning and unsupervised learning as well as explainability.

PhD Student

Karolina’s research interests include gender-biased language detection and statistical methods.


Sagnik is interested in question answering and interpretability of neural black-box models.


This is Ryan. He’s a lecturer at the University of Cambridge and a frequent collaborator of the CopeNLU group.

PhD Student

Yova researches low-resource and cross-lingual learning. She’s a member of the CoAStaL NLP group and co-advised by Isabelle.

PhD Student

Andrea’s main research interests are multilingual learning, with a particular focus on translation-aware word prediction. He is a PhD student at the University of Southern Denmark and co-advised by Isabelle.


Oscar researches automating the assessment of psychological constructs using representation learning. He is an international postdoc affiliated with Lund University as well the University of Copenhagen and Stony Brook University.

PhD Student

Ran researches gender bias detection. He is based at the University of Cambridge and co-advised by Isabelle.


Miryam’s main research interests are syntactic parsing, multilingual NLP and interpretability. She is an international postdoc affiliated with KU Leuven as well as the University of Copenhagen.

PhD Student

Ana is a postdoc in the CoAStaL NLP group. Prior to this, she was a PhD student in the same group from 2017-2021 co-advised by Isabelle, working on question answering.


Johannes is a tenure-track assistant profesor at Aalborg University Copenhagen, prior to which he was a postdoc in CopeNLU from 2017 to 2020, researching multi-lingual and multi-task learning.

PhD Intern

Liesbeth is a PhD Student at KU Leuven, and was visiting CopeNLU in Spring 2020 to work on fact checking.

PhD Intern

Shailza is a PhD Student at the Technical University of Kaiserslautern, and a research assistant at DFKI. She is visiting CopeNLU in Winter/Spring 2021 to work on interpretability.

PhD Intern

Wei Zhao is a PhD Student at TU Darmstadt, and was visiting CopeNLU in Winter 2019 to work on low-resource natural language generation.

PhD Student

Mareike was a member of the CoAStaL NLP group and co-advised by Isabelle, and is now a postdoc in the same group.

PhD Intern

Farhad is a PhD Student at the University of Oslo, and was visiting CopeNLU in Spring 2019 to work on domain adaptation for information extraction.

Research Intern

Zhong Xuan is a student at Yale-NUS College, Singapore, and was visiting CopeNLU in Summer 2019 to work on relation extraction and knowledge base population.

PhD Intern

Luna is a PhD Student at Ghent University, and was visiting CopeNLU in Spring 2019 to work on emotion detection.

PhD Intern

Giannis is a postdoc at Vrije Unversiteit Brussel, and was visiting CopeNLU as a PhD Intern in Spring 2019 to work on joint information extraction.

Research Assistant

Now a machine learning engineer at LEO Innovation Lab.

Recent Publications

More Publications

Modern natural language processing (NLP) methods employ self-supervised pretraining objectives such as masked language modeling to …

Bridging the performance gap between high- and low-resource languages has been the focus of much previous work. Typological features …

Citation count prediction is the task of predicting the number of citations a paper has gained after a period of time. Prior work …

The effectiveness of a language model is influenced by its token representations, which must encode contextual information and handle …

For natural language processing (NLP) tasks such as sentiment or topic classification, currently prevailing approaches heavily rely on …

Recent developments in machine learning have introduced models that approach human performance at the cost of increased architectural …

Adversarial attacks reveal important vulnerabilities and flaws of trained models. One potent type of attack are universal adversarial …

Subjectivity is the expression of internal opinions or beliefs which cannot be objectively observed or verified, and has been shown to …

In practical machine learning settings, the data on which a model must make predictions often come from a different distribution than …

Learning what to share between tasks has been a topic of high importance recently, as strategic sharing of knowledge has been shown to …

Recent Posts

We gave a tutorial including lab session at the first ALPS (Advanced Language Prcoessing School. If you want to learn more about …

Yes, we all have planned to be under palm trees of Punta Cana now and to sip drinks with umbrellas. Let’s make a new plan: an …

The University of Copenhagen is a great place if you’re both interested in high-quality NLP research and a high quality of life.



Learning with Limited Labelled Data

Learning with limited labelled data, including multi-task learning, weakly supervised and zero-shot learning

Stance Detection and Fact Checking

Determine the attitude expressed in a text towards a topic, and use this for automatic evidence-based fact checking

Explainable Machine Learning

Explaining relationships between inputs and outputs of black-box machine learning models

Multilingual Learning

Training models to work well for multiple languages, including low-resource ones

Question Answering

Answering questions automatically, including in conversational settings

Gender Bias Detection

Automatically detecting gendered language, and to what degree attitudes towards entities are influenced by gender bias

Knowledge Base Population

Extract information about entities, phrases and relations between them from text to populate knowledge bases