Grounding word meanings in sensor data: dealing with referential uncertainty

Authors:
Tim Oates
Affiliations:
University of Maryland Baltimore County, Baltimore, MD
Venue:
HLT-NAACL-LWM '04 Proceedings of the HLT-NAACL 2003 workshop on Learning word meaning from non-linguistic data - Volume 6
Year:
2003

Citing 4
Cited 1

Randomization tests

Randomization tests
Empirical methods for artificial intelligence

Empirical methods for artificial intelligence
Wavelets for computer graphics: theory and applications

Wavelets for computer graphics: theory and applications
Grounding knowledge in sensors: unsupervised learning for language and planning

Grounding knowledge in sensors: unsupervised learning for language and planning

Talking robots with LEGO MindStorms

COLING '04 Proceedings of the 20th international conference on Computational Linguistics

Quantified Score

Hi-index	0.00

Visualization

Abstract

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.