@article{monroe2017colors,
 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.},
 author = {Monroe, Will  and Hawkins, Robert X.D.  and Goodman, Noah D.  and
Potts, Christopher},
 issn = {2307-387X},
 journal = {Transactions of the Association for Computational
Linguistics},
 keyword = {},
 link = {https://transacl.org/ojs/index.php/tacl/article/view/1142},
 pages = {325--338},
 title = {Colors in Context: A Pragmatic Neural Model for Grounded
Language Understanding},
 url = {https://nlp.stanford.edu/pubs/monroe2017colors.pdf},
 volume = {5},
 year = {2017}
}