The purpose of COVAX (Contemporary Culture Virtual Archives in XML) financed by the European Commission in IST Programme was to analyse and draw up the technical solutions required to provide access through the Internet to homogeneously-encoded document descriptions of archive, library and museum collections based on the application of XML. The project demonstrated its feasibility through a prototype containing a meaningful sample of all the different types of documents to build a global system for search and retrieval. The aim of this paper is to create in the COVAX system a new presentation of the documents. A system capable of processing markup semantics declarations can act as an interactive environment for testing conjectures and validating hypotheses. Semantics is one of the ways of improving information retrieval performances; we will explore this problem in the COVAX case study. We will investigate the possibility to derive a semantic knowledge from COVAX repositories, in order to improve the site analysis process and the query answering process.