We address the problem of generating adjectives in a text generation system. We distinguish between usages of adjectives informing the hearer of a property of an object and usages expressing an intention of the speaker, or an argumentative orientation. For such argumentative usages we claim that a generator cannot simply map from information in the knowledge base to adjectives. Instead, we identify various knowledge sources necessary to decide whether to use an adjective, what adjective should be selected and what syntactic function it should have we show how these decisions interact with lexical properties of adjectives and the syntax of the clause. We propose a mechanism for adjective selection and illustrate it in the context of the explanation component of the ADVISOR expert system. We describe an implementation of adjective selection using a version of Functional Unification Grammars.
|Title of host publication||Proceedings of the 9th National Conference on Artificial Intelligence, Anaheim, CA, USA, July 14-19, 1991, Volume 1|
|Editors||Thomas L. Dean, Kathleen R. McKeown|
|Publisher||AAAI Press / The MIT Press|
|Number of pages||7|
|State||Published - 1991|