Authorship Style Transfer with Policy Optimization

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Liu, Shuai, Agarwal, Shantanu, May, Jonathan
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866910545239605248
author Liu, Shuai
Agarwal, Shantanu
May, Jonathan
author_facet Liu, Shuai
Agarwal, Shantanu
May, Jonathan
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2403_08043
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Authorship Style Transfer with Policy Optimization
Liu, Shuai
Agarwal, Shantanu
May, Jonathan
Computation and Language
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.
title Authorship Style Transfer with Policy Optimization
topic Computation and Language
url https://arxiv.org/abs/2403.08043