Semantic Web Services (SWS) aim at the automated discovery, selection and orchestration of Web services on the basis of comprehensive, machine-interpretable semantic descriptions. The latter are in principle deployed by multiple possible actors (i.e. service providers and service consumers), and thus, a high level of heterogeneity between distinct SWS annotations is expected. Therefore, mediation between concurrent semantic representations of services is a key requirement to fully implement the SWS vision. In particular, we argue that “semantic-level mediation” is necessary to identify semantic similarities across distinct SWS representations. To this end, we first formalized and then implemented a mediation approach based on the so-called "Mediation Spaces" (MS), which enables the implicit representation of semantic similarities among distinct SWS descriptions. As a result, given a specific SWS approach and the proposed MS, a general purpose algorithm has been implemented to empower SWS selection with the automatic computation of semantic similarities between a given SWS request and a set of SWS offers. A prototypical application illustrates our approach and highlights the benefits w.r.t. current mediation approaches.