SETTP: Style Extraction and Tunable Inference via Dual-level Transferable Prompt Learning
This addresses the problem of limited resources in text style transfer for NLP applications, offering an incremental improvement with specific gains in low-resource settings.
The paper tackles text style transfer in low-resource scenarios by introducing SETTP, a method that uses dual-level transferable prompts, achieving performance comparable to state-of-the-art with only 1/20th of the data and outperforming previous methods by 16.24% in scarce data tasks.
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\%.