English

The red one!: On learning to refer to things based on their discriminative properties

Computation and Language 2016-05-24 v2 Computer Vision and Pattern Recognition

Abstract

As a first step towards agents learning to communicate about their visual environment, we propose a system that, given visual representations of a referent (cat) and a context (sofa), identifies their discriminative attributes, i.e., properties that distinguish them (has_tail). Moreover, despite the lack of direct supervision at the attribute level, the model learns to assign plausible attributes to objects (sofa-has_cushion). Finally, we present a preliminary experiment confirming the referential success of the predicted discriminative attributes.

Keywords

Cite

@article{arxiv.1603.02618,
  title  = {The red one!: On learning to refer to things based on their discriminative properties},
  author = {Angeliki Lazaridou and Nghia The Pham and Marco Baroni},
  journal= {arXiv preprint arXiv:1603.02618},
  year   = {2016}
}

Comments

Accepted as an ACL-short sumbmission