Multi-Pair Text Style Transfer on Unbalanced Data

Abstract

Text-style transfer aims to convert text given in one domain into another by paraphrasing the sentence or substituting the keywords without altering the content. By necessity, state-of-the-art methods have evolved to accommodate nonparallel training data, as it is frequently the case there are multiple data sources of unequal size, with a mixture of labeled and unlabeled sentences. Moreover, the inherent style defined within each source might be distinct. A generic bidirectional (e.g., formal $\iff$ informal) style transfer regardless of different groups may not generalize well to different applications. In this work, we developed a task adaptive meta-learning framework that can simultaneously perform a multi-pair text-style transfer using a single model. The proposed method can adaptively balance the difference of meta-knowledge across multiple tasks. Results show that our method leads to better quantitative performance as well as coherent style variations. Common challenges of unbalanced data and mismatched domains are handled well by this method.

arXiv commentMeta Learning and Its Applications to Natural Language Processing, ACL 2021 Workshop

References in corpus (13)

• Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks
• Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer
• HuggingFace's Transformers: State-of-the-art Natural Language Processing
• CTRL: A Conditional Transformer Language Model for Controllable Generation
• On First-Order Meta-Learning Algorithms
• Plug and Play Language Models: A Simple Approach to Controlled Text Generation
• Preserving Color in Neural Artistic Style Transfer
• Style Transfer as Unsupervised Machine Translation
• Demystifying Neural Style Transfer
• Delete, Retrieve, Generate: A Simple Approach to Sentiment and Style Transfer
• Style Transfer in Text: Exploration and Evaluation
• Learning to Balance: Bayesian Meta-Learning for Imbalanced and Out-of-distribution Tasks
• ST${}^2$: Small-data Text Style Transfer via Multi-task Meta-Learning