Colors in Context: A Pragmatic Neural Model for Grounded Language Understanding

Will Monroe, Robert X.D. Hawkins, Noah D. Goodman, Christopher Potts


Abstract
We present a model of pragmatic referring expression interpretation in a grounded communication task (identifying colors from descriptions) that draws upon predictions from two recurrent neural network classifiers, a speaker and a listener, unified by a recursive pragmatic reasoning framework. Experiments show that this combined pragmatic model interprets color descriptions more accurately than the classifiers from which it is built, and that much of this improvement results from combining the speaker and listener perspectives. We observe that pragmatic reasoning helps primarily in the hardest cases: when the model must distinguish very similar colors, or when few utterances adequately express the target color. Our findings make use of a newly-collected corpus of human utterances in color reference games, which exhibit a variety of pragmatic behaviors. We also show that the embedded speaker model reproduces many of these pragmatic behaviors.
Anthology ID:
Q17-1023
Volume:
Transactions of the Association for Computational Linguistics, Volume 5
Month:
Year:
2017
Address:
Venue:
TACL
SIG:
Publisher:
Note:
Pages:
325–338
Language:
URL:
https://aclanthology.org/Q17-1023
DOI:
10.1162/tacl_a_00064
Bibkey:
Copy Citation:
PDF:
https://aclanthology.org/Q17-1023.pdf
Video:
 https://vimeo.com/238230459