Domain Adaptive Text Style Transfer

08/25/2019
by   Dianqi Li, et al.
0

Text style transfer without parallel data has achieved some practical success. However, in the scenario where less data is available, these methods may yield poor performance. In this paper, we examine domain adaptation for text style transfer to leverage massively available data from other domains. These data may demonstrate domain shift, which impedes the benefits of utilizing such data for training. To address this challenge, we propose simple yet effective domain adaptive text style transfer models, enabling domain-adaptive information exchange. The proposed models presumably learn from the source domain to: (i) distinguish stylized information and generic content information; (ii) maximally preserve content information; and (iii) adaptively transfer the styles in a domain-aware manner. We evaluate the proposed models on two style transfer tasks (sentiment and formality) over multiple target domains where only limited non-parallel data is available. Extensive experiments demonstrate the effectiveness of the proposed model compared to the baselines.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
05/25/2022

Low Resource Style Transfer via Domain Adaptive Meta Learning

Text style transfer (TST) without parallel data has achieved some practi...
research
01/27/2022

Controlling Directions Orthogonal to a Classifier

We propose to identify directions invariant to a given classifier so tha...
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
03/02/2022

Styleverse: Towards Identity Stylization across Heterogeneous Domains

We propose a new challenging task namely IDentity Stylization (IDS) acro...
research
04/10/2023

ITportrait: Image-Text Coupled 3D Portrait Domain Adaptation

Domain adaptation of 3D portraits has gained more and more attention. Ho...
research
12/25/2017

Domain Adaptation Meets Disentangled Representation Learning and Style Transfer

In order to solve the unsupervised domain adaptation problem, some metho...
research
06/01/2020

Latent Domain Learning with Dynamic Residual Adapters

A practical shortcoming of deep neural networks is their specialization ...

Please sign up or login with your details

Forgot password? Click here to reset