Locally organized text generation
Penelope Sibun · Scholarworks (University of Massachusetts Amherst) · 1992
In this thesis I present an architecture for generating extended text. This architecture is implemented in a system, Salix, which incrementally generates natural language texts whose structure is derived from the domain structure of the subject matter. The architecture is composed of data driven domain independent strategies for producing increments of text and metastrategies that combine or choose among all strategies that are applicable at each increment or decide what to do if no strategy applies. Salix's capabilities are demonstrated in generating texts, in the domains of houses and families, that are comparable to descriptions elicited from human speakers. Generating texts describing physical processes has also been explored. The approach to text generation presented here is compared to others in the literature along the dimensions of local organization, incremental generation, coherence, focusing, and domain independence. An argument is made for the approach presented here that locally organizes and incrementally generates coherent texts.