AI Chat AI Image Generator AI Video Text to Speech

What is wrong with style transfer for texts?

08/13/2018

∙

by Alexey Tikhonov, et al.

∙

∙

A number of recent machine learning papers work with an automated style transfer for texts and, counter to intuition, demonstrate that there is no consensus formulation of this NLP task. Different researchers propose different algorithms, datasets and target metrics to address it. This short opinion paper aims to discuss possible formalization of this NLP task in anticipation of a further growing interest to it.

Alexey Tikhonov
25 publications
Ivan P. Yamshchikov
21 publications

page 1

page 2

page 3

page 4

research

∙ 04/28/2022

Russian Texts Detoxification with Levenshtein Editing

Text detoxification is a style transfer task of creating neutral version...

0 Ilya Gusev, et al. ∙

research

∙ 04/04/2019

Evaluating Style Transfer for Text

Research in the area of style transfer for text is currently bottlenecke...

0 Remi Mir, et al. ∙

research

∙ 09/26/2019

Decomposing Textual Information For Style Transfer

This paper focuses on latent representations that could effectively deco...

0 Ivan P. Yamshchikov, et al. ∙

research

∙ 08/19/2019

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

This paper shows that standard assessment methodology for style transfer...

0 Alexey Tikhonov, et al. ∙

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...

0 Alexey Tikhonov, et al. ∙

research

∙ 10/10/2020

Semi-supervised Formality Style Transfer using Language Model Discriminator and Mutual Information Maximization

Formality style transfer is the task of converting informal sentences to...

0 Kunal Chawla, et al. ∙

research

∙ 02/09/2021

Emotion Transfer Using Vector-Valued Infinite Task Learning

Style transfer is a significant problem of machine learning with numerou...

16 Alex Lambert, et al. ∙