English

Canonical Correlation Inference for Mapping Abstract Scenes to Text

Computation and Language 2017-11-21 v2

Abstract

We describe a technique for structured prediction, based on canonical correlation analysis. Our learning algorithm finds two projections for the input and the output spaces that aim at projecting a given input and its correct output into points close to each other. We demonstrate our technique on a language-vision problem, namely the problem of giving a textual description to an "abstract scene".

Keywords

Cite

@article{arxiv.1608.02784,
  title  = {Canonical Correlation Inference for Mapping Abstract Scenes to Text},
  author = {Nikos Papasarantopoulos and Helen Jiang and Shay B. Cohen},
  journal= {arXiv preprint arXiv:1608.02784},
  year   = {2017}
}

Comments

10 pages, accepted to AAAI 2018

R2 v1 2026-06-22T15:15:49.097Z