Using Plan Reasoning in the Generation
R. Michael Young · 1996
Previous work on the generation of natural lan-guage descriptions of complex activities has indi-cated that the unwieldy amount of text needed to describe complete plans makes for ineffective and unnatural descriptions. We argue here that concise and effective text descriptions of plans can be generated by exploiting a model of the hearer’s plan reasoning capabilities. We define a computational model of the hearer’s interpreta-tion process that views the interpretation of plan descriptions as refinement search through a space of partial plans. This model takes into account the hearer’s plan preferences and the resource limitations on her reasoning capabilities to de-termine the completed plans she will construct from a given partial description.