Semantic Processing across Domains – University of Copenhagen

Semantic Processing across Domains is a project funded by the Danish Council for independent research| Humanities for the period 2013 – 2017 with a grant of DKK 5.7 m (DFF-1319-00123). 

The project is concerned with semantic processing and domain adaptation and includes annotation and processing of Danish, and it is a collaborate project between the University of Copenhagen and The Society for Danish Language and Literature.

The project is led by professor Bolette Sandford Pedersen and Associate professor Anders Søgaard, Centre for Language Technology, University of Copenhagen.

More info on the project

Next generation information technology will rely on adequate semantic processing. Extending such technology to Danish requires semantically annotated data, but also more methods that are more robust to data scarcity and domain shifts than current state-of-the-art methods. 

The project partners will develop scalable sense inventories for Danish on the basis of existing lexical resources (The Danish Dictionary and the Danish wordnet, DanNet) and will provide semantic corpus annotations of Danish texts.

The project will go beyond state of the art in recent semantic processing by developing machine learning methods that require less data and are less sensitive to domain shifts.

The semantic models induced from such data by the developed methods will be evaluated in a semantic search engine on the national dictionary site developed at the Society for Language and Literature, as well as in a Danish question-answering platform that has been developed by The University of Copenhagen and The Technical University of Denmark in the ESICT project.