# Massive Styles Transfer with Limited Labeled Data

## TL;DR

This paper introduces a multi-agent system for language style transfer that effectively handles multiple styles with limited labeled data by leveraging unlabeled data and mutual cooperation among style agents.

## Contribution

It proposes a novel multi-agent framework that reduces dependency on labeled data and exploits inter-style relationships for improved transfer performance.

## Key findings

- Outperforms existing methods on multi-style transfer tasks
- Effectively utilizes unlabeled data through denoising auto-encoder and back-translation
- Demonstrates robustness across multiple Bible versions as style datasets

## Abstract

Language style transfer has attracted more and more attention in the past few years. Recent researches focus on improving neural models targeting at transferring from one style to the other with labeled data. However, transferring across multiple styles is often very useful in real-life applications. Previous researches of language style transfer have two main deficiencies: dependency on massive labeled data and neglect of mutual influence among different style transfer tasks. In this paper, we propose a multi-agent style transfer system (MAST) for addressing multiple style transfer tasks with limited labeled data, by leveraging abundant unlabeled data and the mutual benefit among the multiple styles. A style transfer agent in our system not only learns from unlabeled data by using techniques like denoising auto-encoder and back-translation, but also learns to cooperate with other style transfer agents in a self-organization manner. We conduct our experiments by simulating a set of real-world style transfer tasks with multiple versions of the Bible. Our model significantly outperforms the other competitive methods. Extensive results and analysis further verify the efficacy of our proposed system.