Language Technology and Computational Linguistics

The research group ‘Language Technology and Computational Linguistics’ works in the areas of computational linguistics, natural language processing (NLP), and cognitive modelling. An overall research challenge concerns the enrichment of computational language models with linguistic and cognitive information. Language models based on text distribution alone are successful in many NLP tasks, but there are complex scenarios that need a deeper ‘understanding’ of text than current models can master.

Questions addressed are how we can inform models with semantic and pragmatic information known from linguistic theory, with cognitive signals such as eye tracking and EEG traces, and also with data from the visual modality (combining text with images, or speech with gesture).

Another challenge concerns the language technology gap that exists for smaller languages, including Danish, compared to e.g. English, and which must be met by increasing the creation of resources and models for Danish. Included here is the development of good and efficient methods for establishing high-quality datasets and lexical-semantic resources.

Finally, the group works on adapting NLP techniques to assist in different areas of Digital Humanities, an emerging field in the humanities where increasingly more data material has become or needs to be digitized and prepared for further digital processing and statistical analysis.


Following these lines of research, our studies fall into the following focus areas:

Methodologies for Developing NLP Language Resources

We develop principled methods for compiling NLP resources and language models that encompass cultural and societal diversity. We experiment with contextual embeddings in order to examine the correlations between the handcrafted and the statistically generated resources. We work with annotated datasets as well as with methods for building computational resources, including lexical-semantic lexicons.

Computational Cognitive Modelling and Multimodality

Seeks The general goal of this area is to explain the way humans process information by developing computational models capturing aspects of such processing. We focus on computational models of language processing and the extent to which these models make use of cognitive signals and data from the visual gestural modality, and combine them with linguistic knowledge.

NLP and Digital Humanities

This area includes computational NLP models for the analysis of textual data in its widest forms including poems, novels, letters, news articles, scientific articles, or lyrics. We perform a continuous upgrade of our NLP pipelines and corpus tools, in particular for Danish, and work to ensure that appropriate methods and gold standards are compiled for evaluating them.

For more information on the focus areas, the NLP tools developed at the Centre for Language Technology, education in NLP, the CLARIN Infrastructure, and other activities at the Centre, we refer to the Centre’s web page.





Name Title Phone E-mail
Aguirrezabal Zabaleta, Manex Associate Professor +4535324829 E-mail
Al-Laith, Ali Mohammed Ali Postdoc +4535326658 E-mail
Diderichsen, Philip Special Consultant +4535324189 E-mail
Gray, Simon Academic Research Officer +4535337688 E-mail
Hansen, Dorte Haltrup Academic Research Staff +4535329070 E-mail
Henriksen, Lina Research Consultant +4535329082 E-mail
Jongejan, Bart Software Developer +4535329075 E-mail
Maegaard, Bente Emeritus +4535329074 E-mail
Navarretta, Costanza Senior Researcher +4535329079 E-mail
Olsen, Sussi Academic Research Staff +4535329064 E-mail
Paggio, Patrizia Associate Professor +4535329072 E-mail
Pedersen, Bolette Sandford Professor, Deputy Head of Department +4535329078 E-mail
Schneidermann, Nina Skovgaard PhD Fellow +4535331600 E-mail

Affiliated researchers

  • Boye, Kasper 
  • Conroy, Alexander 
  • Diderichsen, Philip 
  • Duncker, Dorthe 
  • Schachtenhaufen, Ruben 

Head of research group