Natural language discourse generation in a support tool for conceptual modeling

Hercules Dalianis

Abstract

The support systems for conceptual modeling of today lack natural language feedback. The paper argues for the need of natural language discourse for the validation of a conceptual model. Based on this conclusion, a suggestion is made on a natural language discourse generation system as a validation tool and also as a support tool in executing a conceptual model. Various appropriate natural language discourses are then proposed in the paper. The proposed texts were analyzed with Hobbs' coherence relations and the discourses could be analysed with fewer coherence relations than the whole theory contains. A discourse grammar is generalized from the analyzed discourses. A suggestion to control the generation is the user's question together with a user model and various feature checking of the grammar. To conclude the paper a support system based on the natural language generation techniques of today and on previous working systems constructed by the author is suggested.

pdf