This paper sets forth some ideas for the evolution of translation tools in the near future. The proposed improvements consist of a closer integration of terminology and sentence databases. In particular, the authors suggest that bilingual sentence databases (translation memories) could be refined by splitting sentences into large [rsquo][rsquo] bricks [lsquo] [lsquo] of text.They also propose a mechanism through which bilingual sentence databases could be generalized by replacing the known terms by variable placeholders, thus yielding technical sentence [rsquo][rsquo]skeletons[lsquo][lsquo]. This latter idea is the most original and the most promising for future implementations. Although these ideas are not yet supported by experiments, the authors believe that they can be implemented using simple techniques, following the general philosophy that such tools should go as far as possible while remaining robust and useful for the human translator.