One of the most basic functions of language is to refer to objects in a shared scene. Modeling reference with continuous representations is challenging because it requires individuation, i.e., tracking and distinguishing an arbitrary number of referents. We introduce a neural network model that, given a definite description and a set of objects represented by natural images, points to the intended object if the expression has a unique referent, or indicates a failure, if it does not. The model, directly trained on reference acts, is competitive with a pipeline manually engineered to perform the same task, both when referents are purely visual, and when they are characterized by a combination of visual and linguistic properties.
@article{arxiv.1606.08777,
title = {"Show me the cup": Reference with Continuous Representations},
author = {Gemma Boleda and Sebastian Padó and Marco Baroni},
journal= {arXiv preprint arXiv:1606.08777},
year = {2019}
}