In recent years, the natural language generation community has begun to mature rapidly and produce sophisticated off-the-shelf surface realizers. A parallel development in the knowledge representation community has been the emergence of large-scale knowledge bases that house tens of thousands of facts encoded in expressive representational languages. Because of the richness of their representations and the sheer volume of their formally encoded knowledge, these knowledge bases offer the promise of significantly improving the quality of natural language generation. However, the representational complexity, scale, and task-independence of these knowledge bases pose great challenges to natural language generators.

We have designed, implemented, and empirically evaluated FARE, a functional realization system that exploits message specifications drawn from large-scale knowledge bases to create functional descriptions, which are expressions that encode both functional information (case assignment) and structural information (phrasal constituent embeddings). Given a message specification, FARE exploits lexical and grammatical annotations on knowledge base objects to construct functional descriptions, which are then converted to text by a surface generator. Two empirical studies---one with an explanation generator and one with a qualitative model builder---suggest that FARE is robust, efficient, expressive, and appropriate for a broad range of applications.

PS

In Proceedings of the Fourth Bar-Ilan Symposium on the Foundations of AI 1995.

@inproceedings{callaway:foundationsai95, title={Robust Natural Language Generation from Large-Scale Knowledge Bases}, author={Charles B. Callaway and James Lester}, booktitle={Proceedings of the Fourth Bar-Ilan Symposium on the Foundations of AI}, url="http://www.cs.utexas.edu/users/ai-lab?callaway:foundationsai95", year={1995} }