Research Talk: Grounding Natural Language References to Unvisited and Hypothetical Locations

October 17, 2013
12:00n - 1:00p
Halligan 209
Speaker: Tom Williams, Tufts University


While much research exists on resolving spatial natural language references to known locations, little work deals with handling references to unknown locations. This presentation introduces and evaluates algorithms integrated into a cognitive architecture that allow an agent to learn about its environment while resolving references to both known and unknown locations, and describes how multiple components in the architecture jointly facilitate these capabilities.