# Style Transfer from Non-Parallel Text by Cross-Alignment

arXiv: https://arxiv.org/abs/1705.09655 · HTML: https://mlsanity.com/paper/1705.09655/

## Key facts

- Cited by 248 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 26 May 2017.

## Built on by (most cited first, 30 of 248)

- [Generative Adversarial Networks](https://mlsanity.com/paper/2203.00667/) (2022)
- [RLPrompt: Optimizing Discrete Text Prompts with Reinforcement Learning](https://mlsanity.com/paper/2205.12548/) (2022)
- [Towards Understanding and Mitigating Social Biases in Language Models](https://mlsanity.com/paper/2106.13219/) (2021)
- [In-context Vectors: Making In Context Learning More Effective and Controllable Through Latent Space Steering](https://mlsanity.com/paper/2311.06668/) (2023)
- [Extracting Latent Steering Vectors from Pretrained Language Models](https://mlsanity.com/paper/2205.05124/) (2022)
- [Challenges and Strategies in Cross-Cultural NLP](https://mlsanity.com/paper/2203.10020/) (2022)
- [Mind the Style of Text! Adversarial and Backdoor Attacks Based on Text Style Transfer](https://mlsanity.com/paper/2110.07139/) (2021)
- [ZeroCap: Zero-Shot Image-to-Text Generation for Visual-Semantic Arithmetic](https://mlsanity.com/paper/2111.14447/) (2021)
- [A Recipe For Arbitrary Text Style Transfer with Large Language Models](https://mlsanity.com/paper/2109.03910/) (2021)
- [Bias in Large Language Models: Origin, Evaluation, and Mitigation](https://mlsanity.com/paper/2411.10915/) (2024)
- [Towards Facilitating Empathic Conversations in Online Mental Health Support: A Reinforcement Learning Approach](https://mlsanity.com/paper/2101.07714/) (2021)
- [Break-It-Fix-It: Unsupervised Learning for Program Repair](https://mlsanity.com/paper/2106.06600/) (2021)
- [Controlled Text Generation as Continuous Optimization with Multiple Constraints](https://mlsanity.com/paper/2108.01850/) (2021)
- [Mix and Match: Learning-free Controllable Text Generation using Energy Language Models](https://mlsanity.com/paper/2203.13299/) (2022)
- [Compression, Transduction, and Creation: A Unified Framework for Evaluating Natural Language Generation](https://mlsanity.com/paper/2109.06379/) (2021)
- [Style Vectors for Steering Generative Large Language Model](https://mlsanity.com/paper/2402.01618/) (2024)
- [Measuring and Controlling Instruction (In)Stability in Language Model Dialogs](https://mlsanity.com/paper/2402.10962/) (2024)
- [XFORMAL: A Benchmark for Multilingual Formality Style Transfer](https://mlsanity.com/paper/2104.04108/) (2021)
- [Text Detoxification using Large Pre-trained Neural Models](https://mlsanity.com/paper/2109.08914/) (2021)
- [Prompt-and-Rerank: A Method for Zero-Shot and Few-Shot Arbitrary Textual Style Transfer with Small Language Models](https://mlsanity.com/paper/2205.11503/) (2022)
- [Teach LLMs to Personalize -- An Approach inspired by Writing Education](https://mlsanity.com/paper/2308.07968/) (2023)
- [Generating Syntactically Controlled Paraphrases without Using Annotated Parallel Pairs](https://mlsanity.com/paper/2101.10579/) (2021)
- [A Causal Lens for Controllable Text Generation](https://mlsanity.com/paper/2201.09119/) (2022)
- [The Shifted and The Overlooked: A Task-oriented Investigation of User-GPT Interactions](https://mlsanity.com/paper/2310.12418/) (2023)
- [Transformer-based Conditional Variational Autoencoder for Controllable Story Generation](https://mlsanity.com/paper/2101.00828/) (2021)
- [MReD: A Meta-Review Dataset for Structure-Controllable Text Generation](https://mlsanity.com/paper/2110.07474/) (2021)
- [DiffusER: Discrete Diffusion via Edit-based Reconstruction](https://mlsanity.com/paper/2210.16886/) (2022)
- [LEWIS: Levenshtein Editing for Unsupervised Text Style Transfer](https://mlsanity.com/paper/2105.08206/) (2021)
- [Controllable Neural Dialogue Summarization with Personal Named Entity Planning](https://mlsanity.com/paper/2109.13070/) (2021)
- [Detoxifying Text with MaRCo: Controllable Revision with Experts and Anti-Experts](https://mlsanity.com/paper/2212.10543/) (2022)

## Abstract (arXiv)

This paper focuses on style transfer on the basis of non-parallel text. This is an instance of a broad family of problems including machine translation, decipherment, and sentiment modification. The key challenge is to separate the content from other aspects such as style. We assume a shared latent content distribution across different text corpora, and propose a method that leverages refined alignment of latent representations to perform style transfer. The transferred sentences from one style should match example sentences from the other style as a population. We demonstrate the effectiveness of this cross-alignment method on three tasks: sentiment modification, decipherment of word substitution ciphers, and recovery of word order.