Ideally, we might hope to improve the performance of our MT systems by improving the system, but it might be even more important to improve performance by looking for a more appropriate application. A survey of the literature on evaluation of MT systems seems to suggest that the success of the evaluation often depends very strongly on the selection of an appropriate application. If the application is well-chosen, then it often becomes fairly clear how the system should be evaluated. Moreover, the evaluation is likely to make the system look good. Conversely, if the application is not clearly identified (or worse, if the application is poorly chosen), then it is often very difficult to find a satisfying evaluation paradigm. We begin our discussion with a brief review of some evaluation metrics that have been tried in the past and conclude that it is difficult to identify a satisfying evaluation paradigm that will make sense over all possible applications. It is probably wise to identify the application first, and then we will be in a much better position to address evaluation questions. The discussion will then turn to the main point, an essay on how to pick a good niche application for state-of-the-art (crummy) machine translation.- 2-1.

While machine translation can successfully tackle some highly restricted sublanguages, it is in most cases more productive to turn to support tools for human translators. The functions taken over by existing translator's workstations are rather peripheral with respect to the core aspects of the translation task. However, recent developments show that it is possible to automatically produce explicit (partial) representations of the translation correspondences that link pairs of source and target texts. These representations called bitexts provide the foundation required for the design of support tools that delve deeper into the realm of translation proper, such as: a) a translation memory that can be accessed by various means, including bilingual concordancing; b) translation critiquing tools capable of detecting correspondence errors such as omissions or deceptive cognates; and c) translator-oriented speech recognition systems capable of taking advantage of correspondence contraints wi...