Answers are grounded in this paper and cite their sources.
We consider the problem of how the meanings of words can be grounded in sensor data.A probabilistic representation for the meanings of words is defined, a method for recovering meanings from observational information about word use in the face of referential uncertainty is described, and empirical results with real utterances and robot sensor data are presented.
No takes yet. Share an insight, caveat, or question.
Tim Oates (2003) studied this question.