Low-Level Linguistic Controls for Style Transfer and Content Preservation

TL;DR

This paper proposes modeling style in text as low-level linguistic controls, enabling neural models to perform style transfer by adjusting features like pronoun and preposition usage while preserving content.

Contribution

It introduces a formal, extendable framework for style as linguistic controls, allowing neural models to manipulate style independently of content in text generation.

Findings

The model reliably responds to linguistic controls.

It fools a style classifier 84% of the time.

Outputs are highly diverse and stylistically distinctive.

Abstract

Despite the success of style transfer in image processing, it has seen limited progress in natural language generation. Part of the problem is that content is not as easily decoupled from style in the text domain. Curiously, in the field of stylometry, content does not figure prominently in practical methods of discriminating stylistic elements, such as authorship and genre. Rather, syntax and function words are the most salient features. Drawing on this work, we model style as a suite of low-level linguistic controls, such as frequency of pronouns, prepositions, and subordinate clause constructions. We train a neural encoder-decoder model to reconstruct reference sentences given only content words and the setting of the controls. We perform style transfer by keeping the content words fixed while adjusting the controls to be indicative of another style. In experiments, we show that the model reliably responds to the linguistic controls and perform both automatic and manual evaluations on style transfer. We find we can fool a style classifier 84% of the time, and that our model produces highly diverse and stylistically distinctive outputs. This work introduces a formal, extendable model of style that can add control to any neural text generation system.