@COMMENT This file was generated by bib2html.pl version 0.90
@COMMENT written by Patrick Riley
@COMMENT This file came from Peter Stone's publication pages at
@COMMENT http://www.cs.utexas.edu/~pstone/papers
@InProceedings{IJCAI16-thomason,
title={Learning Multi-Modal Grounded Linguistic Semantics by Playing {I Spy}},
author={Jesse Thomason and Jivko Sinapov and Maxwell Svetlik and Peter Stone and Raymond Mooney},
booktitle={Proceedings of the 25th international joint conference on Artificial Intelligence (IJCAI)},
location = {New York City, USA},
month = {July},
year = {2016},
abstract = { Grounded language learning bridges words like
‘red’ and ‘square’ with robot perception. The vast
majority of existing work in this space limits robot
perception to vision. In this paper, we build per-
ceptual models that use haptic, auditory, and pro-
prioceptive data acquired through robot exploratory
behaviors to go beyond vision. Our system learns
to ground natural language words describing ob-
jects using supervision from an interactive human-
robot “I Spy” game. In this game, the human and
robot take turns describing one object among sev-
eral, then trying to guess which object the other
has described. All supervision labels were gath-
ered from human participants physically present
to play this game with a robot. We demonstrate
that our multi-modal system for grounding natu-
ral language outperforms a traditional, vision-only
grounding framework by comparing the two on the
“I Spy” task. We also provide a qualitative analysis
of the groundings learned in the game, visualizing
what words are understood better with multi-modal
sensory information as well as identifying learned
word meanings that correlate with physical object
properties (e.g. ‘small’ negatively correlates with
object weight)
},
wwwnote={ Demo Video},
}