Encoding the addressee in the syntax: evidence from English imperative subjects

Imperative subjects in English are puzzling in several respects: null subjects are possible with a definite interpretation, unlike in other clause types; quantificational subjects are often restricted to range over a set containing the addressee and exhibit binding possibilities not readily available to them in declaratives and interrogatives; and third person referential subjects are for most speakers limited to bare noun phrases. On the empirical side, this paper provides a comprehensive discussion of these properties that makes sense of the sometimes contradictory observations found in the literature. On the theoretical side, it argues that the syntactic representation of imperatives contains a functional projection not present in other clause types. This projection plays a role both in preventing the instantiation of a predication relation between the subject and the predicate, and, when sufficiently local, in licensing the special syntactic properties of the subject. This proposal differs from those that view the properties of imperative subjects as deriving uniquely from the semantic or pragmatic component; it can be seen as building on the general intuition of the old performative hypothesis, though recasting it at a level of abstraction that captures more adequately the properties of imperatives.