ABSTRACT
In this paper, we investigate the interaction between linguistic and non-linguistic processes by considering the role of functional reasoning in understanding design specifications written in natural language. We describe KA, an experimental model-based interpretation and design system which understands English language descriptions of the design problems it solves, and examine whether KA’s problem-solving capabilities help i) ascertain the relevance of ambiguous design specifications and ii) identify unspecified relations between design requirements. Our results demonstrate that augmenting language processing with the ability to reason about function along the lines suggested in KA provides effective solutions to these problems in particular as well as to other problems in natural language understanding.
