Generating Connectives

We present an implemented procedure to select an appropriate connective to link two propositions, which is part of a large text generation system. Each connective is defined as a set of constraints between features of flxe propositions it connects. Ore' focus has been to identify pragmatic features flint can be produced by a deep generator to provide a simple representation of connectives. Using these features, we can account for a variety of connective usages, and we can distinguish between similar connectives. We describe how a surfi~ee generator can produce complex sentences when given these features in input. The selection procedure is irnplemented as part of a large functional unification gralmnar. 1. I N T R O I ) U C T I O N : M O T I V A T I O N A language %~:.eration system that produces complex sentences must be able to determine which connective (e.g., "but," "although/' "since," "because," "and," etc.) best links its embedded sentences. Previous text generation systems (McKeown, 1985, Mann, 1984, Davey, 1979, Hovy, 1987) 1 have generally used a notion similar to rhetorical relations to describe the connection between propositions. They make a one-to-one mapping from these relations to connectives for generation (for example, the relation "opposition" would be realized by the connective "but") . In this approach it is difficult to distinguish between similar comlectives (e.g., because vs. since or but vs. although). These connectives can not be used interchangeably, however, and a generation system must be able to make the correct