Towards data-driven ontologies: A filtering approach using keywords and natural language constructs

Creating ontologies is an expensive task. Our vision is that we can automatically generate ontologies based on a set of relevant documents to create a kick-start in ontology creating sessions. In this paper, we focus on enhancing two often used methods, OpenIE and cooccurrences. We evaluate the methods on two document sets, one about pizza and...

Comparison of two data assimilation methods for assessing PM10 exceedances on the European scale

Two different data assimilation techniques have been applied to assess exceedances of the daily and annual mean limit values for PM10 on the regional scale in Europe. The two methods include a statistical interpolation method (SI), based on residual kriging after linear regression of the model, and Ensemble Kalman filtering (EnKF). Both methods...