Decomposing Textual Information For Style Transfer

09/26/2019
by   Ivan P. Yamshchikov, et al.
0

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.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
06/09/2021

A Review of Human Evaluation for Style Transfer

This paper reviews and summarizes human evaluation practices described i...
research
01/21/2022

Text Style Transfer for Bias Mitigation using Masked Language Modeling

It is well known that textual data on the internet and other digital pla...
research
12/20/2022

SimpleStyle: An Adaptable Style Transfer Approach

Attribute-controlled text rewriting, also known as text style-transfer, ...
research
08/19/2019

Style Transfer for Texts: to Err is Human, but Error Margins Matter

This paper shows that standard assessment methodology for style transfer...
research
08/19/2019

Style Transfer for Texts: Retrain, Report Errors, Compare with Rewrites

This paper shows that standard assessment methodology for style transfer...
research
10/08/2019

Prose for a Painting

Painting captions are often dry and simplistic which motivates us to des...
research
08/13/2018

What is wrong with style transfer for texts?

A number of recent machine learning papers work with an automated style ...

Please sign up or login with your details

Forgot password? Click here to reset