Massive Styles Transfer with Limited Labeled Data
This addresses a practical challenge in NLP for real-life applications where multiple style transfers are needed but labeled data is scarce, though it is incremental as it builds on existing techniques like denoising auto-encoders and back-translation.
The paper tackles the problem of language style transfer across multiple styles with limited labeled data by proposing a multi-agent system (MAST) that leverages unlabeled data and inter-task cooperation, achieving significant performance improvements over competitive methods in experiments using Bible versions.
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.