News

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.

A PhD fellowship on gender bias and stance detection is available in CopeNLU. The position is funded by a basic research project on the same topic funded by the Independent Research Fund Denmark (DFF). The fellowship offers the applicant employment as a PhD fellow for a period of three years. The successful candidate will be advised by Isabelle Augenstein and co-advised by Ryan Cotterell (ETH Zurich). Funding for bilateral visits is available. The current call is open until 1 December 2019 for a start in Spring 2020.

25 Marie Skłodowska-Curie PhD fellowships are available at the University of Copenhagen Faculty of Science via the TALENT program. The fellowship offers applicants employment as PhD fellows for a period of three years on a research topic of the fellow’s choice. The current call is open from 15 August to 1 October 2019 for a start date in Spring 2020.

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.

People

.js-id-Members

Assistant Professor

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

Postdoc

Johannes researches multi-lingual and multi-task learning, with a particular focus on exploiting similarities between languages.

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.

Lecturer

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

Ana’s main research interest is question answering, with a particular focus on the customer support domain. She’s a member of the CoAStaL NLP group and co-advised by Isabelle.

PhD Student

Mareike is interested in fact checking and multi-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.

PhD Student

Nils researches low-resource and unsupervised learning. He is based at DFKI Berlin and co-advised by Isabelle.

PhD Intern

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

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 PhD Student at Ghent University, and was visiting CopeNLU in Spring 2019 to work on joint information extraction.

Research Assistant

Now a data scientist at Hypefactors

Recent Publications

More Publications

While state-of-the-art NLP explainability (XAI) methods focus on supervised, per-instance end or diagnostic probing task evaluation[4, …

Emotion lexica are commonly used resources to combat data poverty in automatic emotion detection. However, methodological issues emerge …

Language evolves over time in many ways relevant to natural language processing tasks. For example, recent occurrences of tokens …

We contribute the largest publicly available dataset of naturally occurring factual claims for the purpose of automatic claim …

Digital media enables not only fast sharing of information, but also disinformation. One prominent case of an event leading to …

Task oriented dialogue systems rely heavily on specialized dialogue state tracking (DST) modules for dynamically predicting user intent …

Task oriented dialogue systems rely heavily on specialized dialogue state tracking (DST) modules for dynamically predicting user intent …

Although the vast majority of knowledge bases KBs are heavily biased towards English, Wikipedias do cover very different topics in …

Multi-task learning and self-training are two common ways to improve a machine learning model’s performance in settings with …

The study of linguistic typology is rooted in the implications we find between linguistic features, such as the fact that languages …

Recent Posts

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

Projects

*

Learning with Limited Labelled Data

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

Multilingual Learning

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

Question Answering

Answering questions automatically, including in conversational settings

Stance Detection and Fact Checking

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

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

Contact