SC2: Towards Enhancing Content Preservation and Style Consistency in Long Text Style Transfer

TL;DR

This paper introduces SC2, a novel long text style transfer method that improves content preservation and style consistency through a joint style-content assessment module and a style consistency loss, outperforming existing approaches.

Contribution

The paper proposes a multilayer Joint Style-Content Weighed module and a style consistency loss to enhance content preservation and style consistency in long text style transfer.

Findings

SC2 significantly outperforms baseline methods in content preservation.

The style consistency loss ensures uniform style across multiple generated sentences.

The denoising non-autoregressive decoder accelerates training without sacrificing quality.

Abstract

Text style transfer (TST) aims to vary the style polarity of text while preserving the semantic content. Although recent advancements have demonstrated remarkable progress in short TST, it remains a relatively straightforward task with limited practical applications. The more comprehensive long TST task presents two challenges: (1) existing methods encounter difficulties in accurately evaluating content attributes in multiple words, leading to content degradation; (2) the conventional vanilla style classifier loss encounters obstacles in maintaining consistent style across multiple generated sentences. In this paper, we propose a novel method SC2, where a multilayer Joint Style-Content Weighed (JSCW) module and a Style Consistency loss are designed to address the two issues. The JSCW simultaneously assesses the amounts of style and content attributes within a token, aiming to acquire a lossless content representation and thereby enhancing content preservation. The multiple JSCW layers further progressively refine content representations. We design a style consistency loss to ensure the generated multiple sentences consistently reflect the target style polarity. Moreover, we incorporate a denoising non-autoregressive decoder to accelerate the training. We conduct plentiful experiments and the results show significant improvements of SC2 over competitive baselines. Our code: https://github.com/jiezhao6/SC2.