Situating natural language understanding within experience-based design

Building useful systems with an ability to understand \real" natural language input has long been an elusive goal for Artiicial Intelligence. Well-known problems such as ambiguity, indi-rectness, and incompleteness of natural language inputs have thwarted eeorts to build natural language interfaces to intelligent systems. In this article, we report on our work on a model of understanding natural language design speciications of physical devices such as simple electrical circuits. Our system, called KA, solves the classical problems of ambiguity, incompleteness, and indirectness by exploiting the knowledge and problem-solving processes in the situation of designing simple physical devices. In addition, KA acquires its knowledge structures (apart from a basic ontology of devices) from the results of its problem-solving processes. Thus, KA can be bootstrapped to understand design speciications and user feedback about new devices using the knowledge structures it acquired from similar devices designed previously. In this paper, we report on three investigations in the KA project. Our rst investigation demonstrates that KA can resolve ambiguities in design speciications as well as infer unar-ticulated requirements using the ontology, the knowledge structures, and the problem-solving processes provided by its design situation. The second investigation shows that KA's problem-solving capabilities help ascertain the relevance of indirect design speciications, and identify unspeciied relations between detailed requirements. The third investigation demonstrates the extensibility of KA's theory of natural language understanding by showing that KA can interpret user feedback as well as design requirements. Our results demonstrate that situating language understanding in problem solving, like device design in KA, provides eeective solutions to unresolved problems in natural language processing.