Multi-Pair Text Style Transfer on Unbalanced Data

TL;DR

This paper introduces a task adaptive meta-learning framework for multi-pair text style transfer that effectively handles unbalanced data and domain mismatches, improving transfer quality across multiple style pairs.

Contribution

The work presents a novel meta-learning approach enabling a single model to perform multi-pair style transfer with adaptive balancing of task-specific knowledge.

Findings

Improved quantitative performance over baseline methods.

Effective handling of unbalanced data and domain mismatches.

Produces coherent style variations across multiple style pairs.

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 $\Leftrightarrow$ 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.