It seems highly desirable to use a single representation of linguistic knowledge for both analysis and generation. We argue that the only part of the average NL system's knowledge that we can have any faith in is its vocabulary and, to a lesser extent, its syntactic rules, and we investigate the consequences of this for generation. 1 ANALYSIS Consider a typical NLU system. You give it a piece of text, say: (1) The house I live in is damp. It grinds away, trying out syntactic rules until it has an analysis of the structure of the text. .
