Paper: Sentence Planning For Realtime Navigational Instruction

ACL ID N06-2040
Title Sentence Planning For Realtime Navigational Instruction
Venue Human Language Technologies
Session Short Paper
Year 2006
Authors

In the current work, we focus on systems that provide incremental directions and monitor the progress of mobile users following those directions. Such directions are based on dy- namic quantities like the visibility of reference points and their distance from the user. An intelligent navigation assistant might take ad- vantage of the user’s mobility within the set- ting to achieve communicative goals, for ex- ample, by repositioning him to a point from which a description of the target is easier to produce. Calculating spatial variables over a corpus of human-human data developed for this study, we trained a classi er to detect con- texts in which a target object can be felici- tously described. Our algorithm matched the human subjects with 86% precision.