This paper shows the necessity of distinguishing differentreferential uses of NPs in machine Translation. We propose athree-way distinction between the generic, referential and as-criptive uses of noun phrases (NPs), and argue that this is theminimum necessary to generate articles and number correctly whentranslating form Japanese to English. A detailed algorithm isproposed for determining the referentiality of Japanese NPs, based ona defeasible hierarchy of pragmatic rules that are applied top-down,from the clause to the NP.
展开▼