SETTP: Style Extraction and Tunable Inference via Dual-level Transferable Prompt Learning

TL;DR

SETTP is a novel style transfer method that effectively leverages high-resource style data to perform low-resource style transfer with minimal data, outperforming previous approaches in scarce data scenarios.

Contribution

The paper introduces a dual-level prompt learning framework that transfers style knowledge from high-resource to low-resource settings, reducing data requirements significantly.

Findings

Achieves comparable performance with only 1/20th of the data used by state-of-the-art methods.

Outperforms previous methods by 16.24% in scarce data tasks like writing and role style.

Proposes an automated style similarity evaluation aligned with human judgments.

Abstract

Text style transfer, an important research direction in natural language processing, aims to adapt the text to various preferences but often faces challenges with limited resources. In this work, we introduce a novel method termed Style Extraction and Tunable Inference via Dual-level Transferable Prompt Learning (SETTP) for effective style transfer in low-resource scenarios. First, SETTP learns source style-level prompts containing fundamental style characteristics from high-resource style transfer. During training, the source style-level prompts are transferred through an attention module to derive a target style-level prompt for beneficial knowledge provision in low-resource style transfer. Additionally, we propose instance-level prompts obtained by clustering the target resources based on the semantic content to reduce semantic bias. We also propose an automated evaluation approach of style similarity based on alignment with human evaluations using ChatGPT-4. Our experiments across three resourceful styles show that SETTP requires only 1/20th of the data volume to achieve performance comparable to state-of-the-art methods. In tasks involving scarce data like writing style and role style, SETTP outperforms previous methods by 16.24\%.