A Dual Reinforcement Learning Framework for Unsupervised Text Style Transfer

05/24/2019
by   Fuli Luo, et al.
0

Unsupervised text style transfer aims to transfer the underlying style of text but keep its main content unchanged without parallel data. Most existing methods typically follow two steps: first separating the content from the original style, and then fusing the content with the desired style. However, the separation in the first step is challenging because the content and style interact in subtle ways in natural language. Therefore, in this paper, we propose a dual reinforcement learning framework to directly transfer the style of the text via a one-step mapping model, without any separation of content and style. Specifically, we consider the learning of the source-to-target and target-to-source mappings as a dual task, and two rewards are designed based on such a dual structure to reflect the style accuracy and content preservation, respectively. In this way, the two one-step mapping models can be trained via reinforcement learning, without any use of parallel data. Automatic evaluations show that our model outperforms the state-of-the-art systems by a large margin, especially with more than 8 BLEU points improvement averaged on two benchmark datasets. Human evaluations also validate the effectiveness of our model in terms of style accuracy, content preservation and fluency. Our code and data, including outputs of all baselines and our model are available at https://github.com/luofuli/DualLanST.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
04/29/2020

Politeness Transfer: A Tag and Generate Approach

This paper introduces a new task of politeness transfer which involves c...
research
04/18/2022

Non-Parallel Text Style Transfer with Self-Parallel Supervision

The performance of existing text style transfer models is severely limit...
research
01/31/2019

Unsupervised Text Style Transfer via Iterative Matching and Translation

Text style transfer seeks to learn how to automatically rewrite sentence...
research
09/13/2019

A Neural Approach to Irony Generation

Ironies can not only express stronger emotions but also show a sense of ...
research
06/05/2019

A Hierarchical Reinforced Sequence Operation Method for Unsupervised Text Style Transfer

Unsupervised text style transfer aims to alter text styles while preserv...
research
02/24/2020

Learning to Select Bi-Aspect Information for Document-Scale Text Content Manipulation

In this paper, we focus on a new practical task, document-scale text con...
research
01/24/2023

Audience-Centric Natural Language Generation via Style Infusion

Adopting contextually appropriate, audience-tailored linguistic styles i...

Please sign up or login with your details

Forgot password? Click here to reset