Several researchers have developed properties that ensure
compatibility of a concept similarity or dissimilarity measure with the
formal semantics of Description Logics.
While these authors have highlighted the relevance of the triangle
inequality, none of their proposed dissimilarity measures satisfy it.
In this work we present a theoretical framework for dissimilarity measures
with this property.
Our approach is based on concept relaxations, operators that perform
stepwise generalizations on concepts.
We prove that from any relaxation we can derive a dissimilarity measure
that satisfies a number or properties that are important when comparing
concepts.