In this Programme, two alternative natural language processing modules are developed in parallel: a `grammar-based' (conventional, rule-based) module and a `data-oriented' (statistical, probabilistic, DOP) module. Both of these modules fit into the system architecture of OVIS.
In order to compare the NLP modules, a formal comparative evaluation has been carried out. We describe the set-up of this evaluation, and present the evaluation results. It turns out that the `grammar-based' module obtains much better results for word accuracy and concept accuracy, whereas less computational resources are required.