project summary

The FraCaS project pointed to dialogue as an area in which there should be concentrated effort in future projects concerned with the use of natural language in interaction between humans and machines. The focus of this project will be dialogues between humans and machines that enable the human to make choices in the performance of a certain task (task oriented instructional dialogues). As one example of this we consider Route Planning as a basic scenario. The application of the research to other scenarios (such as Machine Repair and Software Help) will also be considered. We analyze scenarios using a grid of user-machine interaction levels with user interaction levels ranging from physical menu selection to unrestricted spoken questions to the system and machine interaction levels ranging from pre-stored text to generated spoken dialogue contributions.

The project will

  • analyze features of human-human task-oriented instructional dialogue which have to do with the way in which the information states of dialogue participants change during the course of the dialogue
  • examine how such features can be modified in order to simplify the task of enabling human-machine interaction which is both natural and robust, even though it is more restricted than human-human dialogue
  • build a computational model of information revision in task-oriented and instructional dialogues and instructional texts

Printable version of the TRINDI document: