Responding Intelligently to Unparsable Inputs

All natural language systems are likely to receive inputs for which they are unprepared. The system must be able to respond to such inputs by explicitly indicating the reasons the input could not be understood, so that the user will have precise information for trying to rephrase the input. If natural language communication to data bases, to expert consultant systems, or to any other practical system is to be accepted by other than computer personnel, this is an absolute necessity. This paper presents several ideas for dealing with parts of this broad problem. One is the use of presupposition to detect user assumptions. The second is relaxation of tests while parsing. The third is a general technique for responding intelligently when no parse can be found. All of these ideas have been implemented and tested in one of two natural language systems. Some of the ideas are heuristics that might be employed by humans; others are engineering solutions for the problem of practical natural language systems.