# Multi-Style Transfer with Discriminative Feedback on Disjoint Corpus

arXiv: https://arxiv.org/abs/2010.11578 · HTML: https://mlsanity.com/paper/2010.11578/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 22 Oct 2020.

## Built on by (most cited first, 12 of 12)

- [mFACE: Multilingual Summarization with Factual Consistency Evaluation](https://mlsanity.com/paper/2212.10622/) (2022)
- [Prompt-Based Editing for Text Style Transfer](https://mlsanity.com/paper/2301.11997/) (2023)
- [Are You Robert or RoBERTa? Deceiving Online Authorship Attribution Models Using Neural Text Generators](https://mlsanity.com/paper/2203.09813/) (2022)
- [A Call for Standardization and Validation of Text Style Transfer Evaluation](https://mlsanity.com/paper/2306.00539/) (2023)
- [Unsupervised Text Style Transfer via LLMs and Attention Masking with Multi-way Interactions](https://mlsanity.com/paper/2402.13647/) (2024)
- [LMStyle Benchmark: Evaluating Text Style Transfer for Chatbots](https://mlsanity.com/paper/2403.08943/) (2024)
- [Calibrating Likelihoods towards Consistency in Summarization Models](https://mlsanity.com/paper/2310.08764/) (2023)
- [Entailment Relation Aware Paraphrase Generation](https://mlsanity.com/paper/2203.10483/) (2022)
- [Stylistic Retrieval-based Dialogue System with Unparallel Training Data](https://mlsanity.com/paper/2109.05477/) (2021)
- [Adapter-TST: A Parameter Efficient Method for Multiple-Attribute Text Style Transfer](https://mlsanity.com/paper/2305.05945/) (2023)
- [Balancing Effect of Training Dataset Distribution of Multiple Styles for Multi-Style Text Transfer](https://mlsanity.com/paper/2305.15582/) (2023)
- [MSSRNet: Manipulating Sequential Style Representation for Unsupervised Text Style Transfer](https://mlsanity.com/paper/2306.07994/) (2023)

## Abstract (arXiv)

Style transfer has been widely explored in natural language generation with non-parallel corpus by directly or indirectly extracting a notion of style from source and target domain corpus. A common shortcoming of existing approaches is the prerequisite of joint annotations across all the stylistic dimensions under consideration. Availability of such dataset across a combination of styles limits the extension of these setups to multiple style dimensions. While cascading single-dimensional models across multiple styles is a possibility, it suffers from content loss, especially when the style dimensions are not completely independent of each other. In our work, we relax this requirement of jointly annotated data across multiple styles by using independently acquired data across different style dimensions without any additional annotations. We initialize an encoder-decoder setup with transformer-based language model pre-trained on a generic corpus and enhance its re-writing capability to multiple target style dimensions by employing multiple style-aware language models as discriminators. Through quantitative and qualitative evaluation, we show the ability of our model to control styles across multiple style dimensions while preserving content of the input text. We compare it against baselines involving cascaded state-of-the-art uni-dimensional style transfer models.