StoryTrans: Non-Parallel Story Author-Style Transfer with Discourse Representations and Content Enhancing

by   Xuekai Zhu, et al.
Tsinghua University
Wuhan University

Non-parallel text style transfer is an important task in natural language generation. However, previous studies concentrate on the token or sentence level, such as sentence sentiment and formality transfer, but neglect long style transfer at the discourse level. Long texts usually involve more complicated author linguistic preferences such as discourse structures than sentences. In this paper, we formulate the task of non-parallel story author-style transfer, which requires transferring an input story into a specified author style while maintaining source semantics. To tackle this problem, we propose a generation model, named StoryTrans, which leverages discourse representations to capture source content information and transfer them to target styles with learnable style embeddings. We use an additional training objective to disentangle stylistic features from the learned discourse representation to prevent the model from degenerating to an auto-encoder. Moreover, to enhance content preservation, we design a mask-and-fill framework to explicitly fuse style-specific keywords of source texts into generation. Furthermore, we constructed new datasets for this task in Chinese and English, respectively. Extensive experiments show that our model outperforms strong baselines in overall performance of style transfer and content preservation.


page 1

page 2

page 3

page 4


Enhancing Content Preservation in Text Style Transfer Using Reverse Attention and Conditional Layer Normalization

Text style transfer aims to alter the style (e.g., sentiment) of a sente...

GTAE: Graph-Transformer based Auto-Encoders for Linguistic-Constrained Text Style Transfer

Non-parallel text style transfer has attracted increasing research inter...

InfoStyler: Disentanglement Information Bottleneck for Artistic Style Transfer

Artistic style transfer aims to transfer the style of an artwork to a ph...

SE-DAE: Style-Enhanced Denoising Auto-Encoder for Unsupervised Text Style Transfer

Text style transfer aims to change the style of sentences while preservi...

Low-Level Linguistic Controls for Style Transfer and Content Preservation

Despite the success of style transfer in image processing, it has seen l...

Studying the role of named entities for content preservation in text style transfer

Text style transfer techniques are gaining popularity in Natural Languag...

BACON: Deep-Learning Powered AI for Poetry Generation with Author Linguistic Style Transfer

This paper describes BACON, a basic prototype of an automatic poetry gen...

Please sign up or login with your details

Forgot password? Click here to reset