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

TL;DR

StoryTrans is a novel model for non-parallel story style transfer that uses discourse representations and a mask-and-fill approach to better preserve content and transfer author styles at the discourse level.

Contribution

The paper introduces a discourse-level style transfer model for stories, with new datasets and techniques to disentangle style from content and enhance content preservation.

Findings

Outperforms baselines in style transfer quality

Effectively disentangles style and content representations

Improves content preservation in long texts

Abstract

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.