arxivst stuff from arxiv that you should probably bookmark

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

Abstract · Mar 29, 2017 18:15 ·

cs-cl

Arxiv Abstract

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

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. 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.

Read the paper (pdf) »