Paper: A Situated Context Model for Resolution and Generation of Referring Expressions

ACL ID W09-0622
Title A Situated Context Model for Resolution and Generation of Referring Expressions
Venue European Workshop on Natural Language Generation
Session
Year 2009
Authors

The background for this paper is the aim to build robotic assistants that can “natu- rally” interact with humans. One prereq- uisite for this is that the robot can cor- rectly identify objects or places a user refers to, and produce comprehensible ref- erences itself. As robots typically act in environments that are larger than what is immediately perceivable, the problem arises how to identify the appropriate con- text, against which to resolve or produce a referring expression (RE). Existing al- gorithms for generating REs generally by- pass this problem by assuming a given context. In this paper, we explicitly ad- dressthisproblem, proposingamethodfor context determination in large-scale space. We show how it can be applied both for re- solving and producing REs.