• A
  • A
  • A
  • ABC
  • ABC
  • ABC
  • А
  • А
  • А
  • А
  • А
Regular version of the site

Book chapter

Decomposing Textual Information For Style Transfer

P. 128-137.
Ivan P. Yamshchikov, Shibaev V., Nagaev A., Jost J., Tikhonov A.

This paper focuses on latent representations that could effectively decompose different aspects of textual information. Using a framework of style transfer for texts, we propose several empirical methods to assess information decomposition quality. We validate these methods with several state-of-the-art textual style transfer methods. Higher quality of information decomposition corresponds to higher performance in terms of bilingual evaluation understudy (BLEU) between output and human-written reformulations.

In book

Association for Computational Linguistics, 2019.