Abstract
In this paper we consider the problem of retrieving the concepts of an ontology that are most relevant to a given textual query. In our setting the concepts are associated with textual fragments, such as labels, descriptions, and links to other relevant concepts. The main task to be solved is the definition of a similarity measure between the single text of the query and the set of texts associated with an ontology concept. We experimentally study this problem on a particular scenario with a socio-pedagogic domain ontology and Italian language texts. We investigate how the basic cosine similarity measure on the bag-of-words text representations can be improved in three distinct ways by (i) taking into account the context of the ontology nodes, (ii) using the linear combination of various measures, and (iii) exploiting semantic resources. The experimental evaluation confirms the improvement of the presented methods upon the baseline. Beside discussing some issues to consider in applying these methods, we point out some directions for further improvement.