# Syntax Matters! Syntax-Controlled in Text Style Transfer

arXiv: https://arxiv.org/abs/2108.05869 · HTML: https://mlsanity.com/paper/2108.05869/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 33 references that are in the map.
- First posted on arXiv 12 Aug 2021.

## Builds on (most cited first, 25 of 25)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation](https://mlsanity.com/paper/1406.1078/) (2014)
- [Auto-Encoding Variational Bayes](https://mlsanity.com/paper/1312.6114/) (2013)
- [Categorical Reparameterization with Gumbel-Softmax](https://mlsanity.com/paper/1611.01144/) (2016)
- [Convolutional Neural Networks for Sentence Classification](https://mlsanity.com/paper/1408.5882/) (2014)
- [Toward Controlled Generation of Text](https://mlsanity.com/paper/1703.00955/) (2017)
- [Style Transfer from Non-Parallel Text by Cross-Alignment](https://mlsanity.com/paper/1705.09655/) (2017)
- [Dear Sir or Madam, May I introduce the GYAFC Dataset: Corpus, Benchmarks and Metrics for Formality Style Transfer](https://mlsanity.com/paper/1803.06535/) (2018)
- [Delete, Retrieve, Generate: A Simple Approach to Sentiment and Style Transfer](https://mlsanity.com/paper/1804.06437/) (2018)
- [Style Transfer in Text: Exploration and Evaluation](https://mlsanity.com/paper/1711.06861/) (2017)
- [Encoding Sentences with Graph Convolutional Networks for Semantic Role Labeling](https://mlsanity.com/paper/1703.04826/) (2017)
- [Disentangled Representation Learning for Non-Parallel Text Style Transfer](https://mlsanity.com/paper/1808.04339/) (2018)
- [Style Transformer: Unpaired Text Style Transfer without Disentangled Latent Representation](https://mlsanity.com/paper/1905.05621/) (2019)
- [Graph Convolutional Encoders for Syntax-aware Neural Machine Translation](https://mlsanity.com/paper/1704.04675/) (2017)
- [A Probabilistic Formulation of Unsupervised Text Style Transfer](https://mlsanity.com/paper/2002.03912/) (2020)
- [A Dual Reinforcement Learning Framework for Unsupervised Text Style Transfer](https://mlsanity.com/paper/1905.10060/) (2019)
- [Content preserving text generation with attribute controls](https://mlsanity.com/paper/1811.01135/) (2018)
- [Regularizing Neural Machine Translation by Target-bidirectional Agreement](https://mlsanity.com/paper/1808.04064/) (2018)
- [Adversarial Text Generation via Feature-Mover's Distance](https://mlsanity.com/paper/1809.06297/) (2018)
- [Domain Adaptive Text Style Transfer](https://mlsanity.com/paper/1908.09395/) (2019)
- [On Learning Text Style Transfer with Direct Rewards](https://mlsanity.com/paper/2010.12771/) (2020)
- [SHAPED: Shared-Private Encoder-Decoder for Text Style Adaptation](https://mlsanity.com/paper/1804.04093/) (2018)
- [Text Style Transfer: A Review and Experimental Evaluation](https://mlsanity.com/paper/2010.12742/) (2020)
- [Biomedical and Clinical English Model Packages in the Stanza Python NLP Library](https://mlsanity.com/paper/2007.14640/) (2020)

## Built on by (most cited first, 3 of 3)

- [ChatGPT vs Human-authored Text: Insights into Controllable Text Summarization and Sentence Style Transfer](https://mlsanity.com/paper/2306.07799/) (2023)
- [ProSwitch: Knowledge-Guided Instruction Tuning to Switch Between Professional and Non-Professional Responses](https://mlsanity.com/paper/2403.09131/) (2024)
- [Steered Generation via Gradient Descent on Sparse Features](https://mlsanity.com/paper/2502.18644/) (2025)

## Abstract (arXiv)

Existing text style transfer (TST) methods rely on style classifiers to disentangle the text's content and style attributes for text style transfer. While the style classifier plays a critical role in existing TST methods, there is no known investigation on its effect on the TST methods. In this paper, we conduct an empirical study on the limitations of the style classifiers used in existing TST methods. We demonstrate that the existing style classifiers cannot learn sentence syntax effectively and ultimately worsen existing TST models' performance. To address this issue, we propose a novel Syntax-Aware Controllable Generation (SACG) model, which includes a syntax-aware style classifier that ensures learned style latent representations effectively capture the syntax information for TST. Through extensive experiments on two popular TST tasks, we show that our proposed method significantly outperforms the state-of-the-art methods. Our case studies have also demonstrated SACG's ability to generate fluent target-style sentences that preserved the original content.