Structured Content Preservation for Unsupervised Text Style Transfer

Abstract

Text style transfer aims to modify the style of a sentence while keeping its content unchanged. Recent style transfer systems often fail to faithfully preserve the content after changing the style. This paper proposes a structured content preserving model that leverages linguistic information in the structured fine-grained supervisions to better preserve the style-independent content during style transfer. In particular, we achieve the goal by devising rich model objectives based on both the sentence's lexical information and a language model that conditions on content. The resulting model therefore is encouraged to retain the semantic meaning of the target sentences. We perform extensive experiments that compare our model to other existing approaches in the tasks of sentiment and political slant transfer. Our model achieves significant improvement in terms of both content preservation and style transfer in automatic and human evaluation.

Cited by in corpus (8)

• Style Transfer for Texts: Retrain, Report Errors, Compare with Rewrites
• Formality Style Transfer with Hybrid Textual Annotations
• Style-transfer and Paraphrase: Looking for a Sensible Semantic Similarity Metric
• Decomposing Textual Information For Style Transfer
• Improving GAN Training with Probability Ratio Clipping and Sample Reweighting
• From Theories on Styles to their Transfer in Text: Bridging the Gap with a Hierarchical Survey
• IMaT: Unsupervised Text Attribute Transfer via Iterative Matching and Translation
• DGST: a Dual-Generator Network for Text Style Transfer