Throughout the previous chapters, we have demonstrated that MWEs are a source of errors for machine translation (MT) systems and for human non-native speakers of a language. As Manning and Schütze (1999, p. 184) point out, “a nice way to test whether a combination is a collocation [MWE] is to translate it into another language. If we cannot translate the combination word by word, then there is evidence that we are dealing with a collocation”. In Sect. 2. 3. 2, we argue that the fact that MWEs cannot be translated word-for-word is a consequence of their limited syntactic and semantic compositionality. Adequate solutions for the variable syntactic/semantic fixedness of MWEs are not easy to find, especially in the context of statistical MT models. However, for high quality MT, it is important to detect MWEs, to disambiguate them semantically and to treat them appropriately in order to avoid generating unnatural translations or losing information.