When people use natural language in natural settings, they often use it ungrammatical-ly, leaving out or repeating words, breaking off and restarting, speaking in fragments, etc. Their human listeners are usually able to cope with these deviations with little difficulty. If a computer system is to accept natural language input from its users on a routine… (More)
A number of projects at the Carnegie-Mellon University Computer Science Department address issues in Natural Language Processing. Since several of these projects share rescarchers and a similar view of the world, we have listed them in a single summary. Our general interests are in robust man-machine interfaces and the modelling of human dialogs.