# Structured Content Preservation for Unsupervised Text Style Transfer

arXiv: https://arxiv.org/abs/1810.06526 · HTML: https://mlsanity.com/paper/1810.06526/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 15 Oct 2018.

## Built on by (most cited first, 10 of 10)

- [A Review of Text Style Transfer using Deep Learning](https://mlsanity.com/paper/2109.15144/) (2021)
- [Don't Take It Literally: An Edit-Invariant Sequence Loss for Text Generation](https://mlsanity.com/paper/2106.15078/) (2021)
- [Boosting Distress Support Dialogue Responses with Motivational Interviewing Strategy](https://mlsanity.com/paper/2305.10195/) (2023)
- [Political Depolarization of News Articles Using Attribute-aware Word Embeddings](https://mlsanity.com/paper/2101.01391/) (2021)
- [StyleKQC: A Style-Variant Paraphrase Corpus for Korean Questions and Commands](https://mlsanity.com/paper/2103.13439/) (2021)
- [From Theories on Styles to their Transfer in Text: Bridging the Gap with a Hierarchical Survey](https://mlsanity.com/paper/2110.15871/) (2021)
- [GTAE: Graph-Transformer based Auto-Encoders for Linguistic-Constrained Text Style Transfer](https://mlsanity.com/paper/2102.00769/) (2021)
- [Rethinking Crowd Sourcing for Semantic Similarity](https://mlsanity.com/paper/2109.11969/) (2021)
- [Generation, Evaluation, and Explanation of Novelists' Styles with Single-Token Prompts](https://mlsanity.com/paper/2511.20459/) (2025)
- [RT-SFT: Text Style Transfer from Non-Parallel Corpora by Roundtrip Translation](https://mlsanity.com/paper/2602.15013/) (2026)

## Abstract (arXiv)

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.