Modelling Spatio-Temporal Comprehension in Situated Human-Robot Dialogue as Reasoning about Intentions and Plans.

摘要

The article presents an approach to modeling spatio-temporal comprehension in situated dialogue. The approach combines linguistic reasoning with reasoning about intentions and plans during incremental interpretation of dialogue moves. The article explores how intention-directed planning can prime selectional attention in utterance comprehension by disam-biguating linguistic analyses on the basis of plan availability, and by raising expectations what action(s) may be mentioned next. Also, planning can complement linguistic analyses with details on spatiotemporal-causal structure established in plan-ning inferences. This makes such inferences available for fu-ture referencing in the discourse context. 1