Exploring Contextual Word-level Style Relevance for Unsupervised Style Transfer

by   Chulun Zhou, et al.

Unsupervised style transfer aims to change the style of an input sentence while preserving its original content without using parallel training data. In current dominant approaches, owing to the lack of fine-grained control on the influence from the target style,they are unable to yield desirable output sentences. In this paper, we propose a novel attentional sequence-to-sequence (Seq2seq) model that dynamically exploits the relevance of each output word to the target style for unsupervised style transfer. Specifically, we first pretrain a style classifier, where the relevance of each input word to the original style can be quantified via layer-wise relevance propagation. In a denoising auto-encoding manner, we train an attentional Seq2seq model to reconstruct input sentences and repredict word-level previously-quantified style relevance simultaneously. In this way, this model is endowed with the ability to automatically predict the style relevance of each output word. Then, we equip the decoder of this model with a neural style component to exploit the predicted wordlevel style relevance for better style transfer. Particularly, we fine-tune this model using a carefully-designed objective function involving style transfer, style relevance consistency, content preservation and fluency modeling loss terms. Experimental results show that our proposed model achieves state-of-the-art performance in terms of both transfer accuracy and content preservation.


page 1

page 2

page 3

page 4


StyleFlow: Disentangle Latent Representations via Normalizing Flow for Unsupervised Text Style Transfer

Text style transfer aims to alter the style of a sentence while preservi...

The Daunting Task of Real-World Textual Style Transfer Auto-Evaluation

The difficulty of textual style transfer lies in the lack of parallel co...

Unsupervised Text Style Transfer via Iterative Matching and Translation

Text style transfer seeks to learn how to automatically rewrite sentence...

Learning from Bootstrapping and Stepwise Reinforcement Reward: A Semi-Supervised Framework for Text Style Transfer

Text style transfer is an important task in controllable language genera...

Style Obfuscation by Invariance

The task of obfuscating writing style using sequence models has previous...

Generic resources are what you need: Style transfer tasks without task-specific parallel training data

Style transfer aims to rewrite a source text in a different target style...

Challenges in Emotion Style Transfer: An Exploration with a Lexical Substitution Pipeline

We propose the task of emotion style transfer, which is particularly cha...

Please sign up or login with your details

Forgot password? Click here to reset