SOTAVerified

Decomposing Textual Information For Style Transfer

2019-09-26WS 2019Unverified0· sign in to hype

Ivan P. Yamshchikov, Viacheslav Shibaev, Aleksander Nagaev, Jürgen Jost, Alexey Tikhonov

Unverified — Be the first to reproduce this paper.

Reproduce

Abstract

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.

Tasks

Reproductions