Kristina Striegnitz, Paul Tepper, Andrew Lovett, Justine
Cassell:
Knowledge Representation for Generating
Locating Gestures in Route Directions
Abstract
When humans give route directions, they use gestures to indicate the location
of landmarks. Examining such locating gestures in a corpus of direction giving
dialogues shows that the speaker takes one of several perspectives when producing
them. They may locate the landmark with respect to the speaker, with respect
to the person following the route, or with respect to other landmarks, depending
on the function of the discourse segment these gestures occur in. Since these
gestures are so prevalent in direction-giving, in this paper we address the
kinds of dialogue information and knowledge representation that would be
needed to automatically generate them.
|
