Canonical Correlation Inference for Mapping Abstract Scenes to Text

Authors

  • Nikos Papasarantopoulos University of Edinburgh
  • Helen Jiang Stanford University
  • Shay Cohen University of Edinburgh

DOI:

https://doi.org/10.1609/aaai.v32i1.11958

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".

AAAI 2018 Proceedings Cover

Downloads

Published

2018-04-27

How to Cite

Papasarantopoulos, N., Jiang, H., & Cohen, S. (2018). Canonical Correlation Inference for Mapping Abstract Scenes to Text. Proceedings of the AAAI Conference on Artificial Intelligence, 32(1). https://doi.org/10.1609/aaai.v32i1.11958

Issue

Vol. 32 No. 1 (2018): Thirty-Second AAAI Conference on Artificial Intelligence

Section

Main Track: NLP and Machine Learning