Machine translation of prepositions is a difficult task, and compared to the translation of vocabulary words, little work has been done, to date, in this area. This project suggests to address the problem using a semantic framework for the interpretation of the surrounding elements of a preposition in the source language. This framework, called Use Types, will reduce the set of possible prepositions in the target language, therefore helping the translation process. This approach is not language dependent, but we focus, here, on English and Chinese, and we also specifically look at three prepositions: in, on and at. The Use Types semantic framework are explained in details. Machine learning experiments are designed and conducted in which WordNet is employed to lead to an automatic discovery of the Use Types.