What is wrong with style transfer for texts?

Abstract

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.

References in corpus (2)

• Style Transfer from Non-Parallel Text by Cross-Alignment
• Unsupervised Neural Machine Translation

Cited by in corpus (4)

• Controllable Unsupervised Text Attribute Transfer via Editing Entangled Latent Representation
• Style Transfer for Texts: Retrain, Report Errors, Compare with Rewrites
• Decomposing Textual Information For Style Transfer
• From Theories on Styles to their Transfer in Text: Bridging the Gap with a Hierarchical Survey