An utterance may be syntactically and semantIcally well-formed yet violate the pragmatic rules of the world model. This paper presents a context-based strateEy for constructing a cooperative but limited response to pragmatlcally illformed queries. Sug~estlon heuristics use a context model of the speaker's task inferred from the preceding dialogue to propose revisions to the speaker's ill-formed query. Selection heuristics then evaluate these suggestions based upon semantic and relevance criteria. .
