Combinatorial and Relational Network as Toolkit for Dutch Language Technology


Cornetto builds a lexical database for Dutch. The database contains both vertical and horizontal semantic relations and combinatorial lexical constraints such as multiword expressions, idioms and collocations on the one hand, and lexical functions and frames on the other. The concepts will be aligned with the English WordNet.

The role of LIIR in this project regards the development of a toolkit for the automatic acquisition of new concepts and relations from corpora and the extraction of domain-specific sublexica in the subfields of law and medicine.


In this project we have collaborated with the Vrije Universiteit Amsterdam (Prof. Piek Vossen), the Universiteit van Amsterdam (Prof. Maarten de Rijke), Van Dale Lexicografie, and Irion Technologies.


We have developed a language independent toolkit for collocation detection in natural language texts, which integrates several statistical association techniques.

Period From 2006-04-01 to 2008-06-30.
Financed by Nederlandse Taalunie Stevin ST-05-39
Supervised by Marie-Francine Moens
Staff Erik Boiy
Contact Erik Boiy

More information can be found on the project website


  1. BOIY, Erik, DESCHACHT, Koen & MOENS Marie-Francine Learning Visual Entities and their Visual Attributes from Text Corpora In Proceedings of the 5th International Workshop on Text-based Information Retrieval . IEEE Computer Society Press. 2008
  2. BOIY, Erik & MOENS, Marie-Francine Extracting Domain-Specific Collocations for the Dutch WordNet . Technical Report, 27 p. July 2008
  3. VOSSEN, P., VAN DER VLIET, H., MAKS, I., SEGERS, R., MOENS, M.-F., HOFMANN K., SANG E.T.K. & DE RIJKE, M. Cornetto: A Combinatorial Lexical Semantic Database for Dutch. In P. Spyns (Ed.), Essential Speech and Language Technology for Dutch: Resources, Tools and Applications. Berlin: Springer. 2013

Back to all projects