Abstract
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.
Highlights
Text style transfer, which aims to edit an input sentence with the desired style while preserving style-irrelevant content, has received increasing attention in recent years
Our contributions in this paper are threefold: (i) We explore a challenging domain adaptation problem for text style transfer by leveraging massively-available data from other domains. (ii) We introduce simple text style transfer models that preserve content and translate text adaptively into target-domain-specific terms. (iii) We demonstrate through extensive experiments the robustness of these methods for style transfer tasks on multiple target domains where only limited non-parallel data is available
We evaluate the effectiveness of our Domain Adaptive Style Transfer (DAST) models based on three automatic metrics: (i) Content Preservation
Summary
Text style transfer, which aims to edit an input sentence with the desired style while preserving style-irrelevant content, has received increasing attention in recent years. The recent surge of deep generative models (Kingma and Welling, 2013; Goodfellow et al, 2014) has spurred progress in text style transfer without parallel data by learning disentanglement (Hu et al, 2017; Shen et al, 2017; Fu et al, 2018; Li et al, 2018; Prabhumoye et al, 2018). These methods typically require massive amounts of data (Subramanian et al, 2018), and may perform poorly in limited data scenarios
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.