2 papers by CopeNLU authors are accepted to appear at AAAI 2021, on explanation generation, as well as on cross-lingual stance detection.

On 1 September 2021, the DFF Sapere Aude project EXPANSE on ‘Learning to Explain Attitudes on Social Media’ is kicking off, and four new members are joining our group.

3 papers by CopeNLU authors are accepted to appear at EMNLP 2021, on stance detection, exaggeration detection, and on counterfactually augmented data.

A paper by CopeNLU authors on multi-hop fact checking is accepted to appear at IJCAI.

2 papers by CopeNLU authors are accepted to appear at ACL 2021, on interpretability, as well as on scientific document understanding.

A paper by CopeNLU authors on typological blinding of cross-lingual models is accepted to appear at EACL.

2 PhD fellowships and 2 postdoctoral positions on explainable stance detection are available in CopeNLU. The positions are funded by a DFF Sapere Aude research leader fellowship.

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.



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.

PhD Student

Erik’s main research interests are question answering and explainability.


Lucie’s research interests include supporting lower-resourced language communities (including Wikipedia and Wikidata) with NLP, and multilingual knowledge graphs.

PhD Student

Nadav’s research interests include improving the trustworthiness and usefulness of deep models in the NLP domain.


Thea is a MSc Student in Cognitive Science at Aarhus University, visiting CopeNLU in Autumn 2022 to work on gender bias detection.


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


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.


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

Nodens is a PhD student at the University of Edinburgh, interested in interpretability and bio-inspired models.

PhD Intern

Klim is a PhD Student at Ghent University. He was visiting CopeNLU in Spring 2022 to work on entity linking.


Sagnik is a postdoctoral researcher at the University of Michigan. He was a postdoctoral researcher in CopeNLU from 2020 to 2022, working on question answering and interpretability of neural black-box models.

PhD Intern

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

PhD Student

Yova was a PhD student in the CoAStaL NLP group researching low-resource and cross-lingual learning, co-advised by Isabelle. She is now a postdoc in the same group.

PhD Student

Ana is a senior data scientist at Halfspace, Copenhagen. Prior to this, she was a PhD student in the CoAStaL NLP group from 2017-2021 co-advised by Isabelle, working on question answering.

PhD Student

Andrea’s main research interests are multilingual learning and language modelling. He was a PhD student at the University of Southern Denmark and co-advised by Isabelle.


Johannes is an associate professor at Aalborg University Copenhagen. 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

Wei Zhao is a postdoctoral researcher at Heidelberg University, 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, researching disinformation detection and co-advised by Isabelle, and is now a researcher at DFKI.

PhD Intern

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

Research Intern

Zhong Xuan is a data scientist at Grab, 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 principal data scientist at Clarivate, 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 Omhu.

Recent Publications

More Publications

Detecting attitudes expressed in texts, also known as stance detection, has become an important task for the detection of false …

Counterfactually Augmented Data (CAD) aims to improve out-of-domain generalizability, an indicator of model robustness. The improvement …

The success of multilingual pre-trained models is underpinned by their ability to learn representations shared by multiple languages …

Automating the fact checking (FC) process relies on information obtained from external sources. In this work, we posit that it is …

Language embeds information about social, cultural, and political values people hold. Prior work has explored social and potentially …

Automated scientific fact checking is difficult due to the complexity of scientific language and a lack of significant amounts of …

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

This paper presents the Multitask, Multilingual, Multimodal Language Generation COST Action – Multi3Generation (CA18231), an …

Learning scientific document representations can be substantially improved through contrastive learning objectives, where the challenge …

The success of pre-trained contextualized representations has prompted researchers to analyze them for the presence of linguistic …

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

Gender Bias Detection

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

Multilingual Learning

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

Scholarly Data Processing

Automatically processing scholarly data to assist researchers in finding publications, writing better papers, or tracking their impact.

Question Answering

Answering questions automatically, including in conversational settings

Knowledge Base Population

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