Authorship Style Transfer with Policy Optimization
This addresses the challenge of textual style transfer for applications like content adaptation when only a few target examples are available, representing an incremental improvement over existing methods.
The paper tackles the problem of authorship style transfer with limited target style examples by proposing a two-stage tune-and-optimize technique, achieving results that outperform state-of-the-art baseline models in low-resource settings.
Authorship style transfer aims to rewrite a given text into a specified target while preserving the original meaning in the source. Existing approaches rely on the availability of a large number of target style exemplars for model training. However, these overlook cases where a limited number of target style examples are available. The development of parameter-efficient transfer learning techniques and policy optimization (PO) approaches suggest lightweight PO is a feasible approach to low-resource style transfer. In this work, we propose a simple two-stage tune-and-optimize technique for low-resource textual style transfer. We apply our technique to authorship transfer as well as a larger-data native language style task and in both cases find it outperforms state-of-the-art baseline models.