Juliet C. Bourne
Adequate instructions are essential to the correct performance of actions. An instruction is adequate if its action(s) and objects are identified sufficiently and unambiguously, given the instruction’s context. For instance, the instruction Turn the knob would be inadequate if, in the context, more than one knob or one way of turning a knob were salient. However, even if the knob and the manner of turning were uniquely identifiable, the instruction could still be inadequate since it does not tell the reader when to stop turning the knob. What is missing here is the termination information for the action, or when the performance of the action is to end. Conveying such information in automated text generation is the focus of my research. I consider how to incorporate termination information into an action representation and how to generate adequate instructions from instances of the action representation, including how tochoose appropriate expressions for conveying action termination.