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

arXiv: https://arxiv.org/abs/2208.13423 · HTML: https://mlsanity.com/paper/2208.13423/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 28 of its 46 references that are in the map.
- First posted on arXiv 29 Aug 2022.

## Builds on (most cited first, 28 of 28)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [BERTScore: Evaluating Text Generation with BERT](https://mlsanity.com/paper/1904.09675/) (2019)
- [Neural Machine Translation by Jointly Learning to Align and Translate](https://mlsanity.com/paper/1409.0473/) (2014)
- [Hierarchical Neural Story Generation](https://mlsanity.com/paper/1805.04833/) (2018)
- [A Corpus and Evaluation Framework for Deeper Understanding of Commonsense Stories](https://mlsanity.com/paper/1604.01696/) (2016)
- [Style Transfer from Non-Parallel Text by Cross-Alignment](https://mlsanity.com/paper/1705.09655/) (2017)
- [Plan-And-Write: Towards Better Automatic Storytelling](https://mlsanity.com/paper/1811.05701/) (2018)
- [Reformulating Unsupervised Style Transfer as Paraphrase Generation](https://mlsanity.com/paper/2010.05700/) (2020)
- [Disentangled Representation Learning for Non-Parallel Text Style Transfer](https://mlsanity.com/paper/1808.04339/) (2018)
- [HIBERT: Document Level Pre-training of Hierarchical Bidirectional Transformers for Document Summarization](https://mlsanity.com/paper/1905.06566/) (2019)
- [Style Transformer: Unpaired Text Style Transfer without Disentangled Latent Representation](https://mlsanity.com/paper/1905.05621/) (2019)
- [Polite Dialogue Generation Without Parallel Data](https://mlsanity.com/paper/1805.03162/) (2018)
- [Unpaired Sentiment-to-Sentiment Translation: A Cycled Reinforcement Learning Approach](https://mlsanity.com/paper/1805.05181/) (2018)
- ["Mask and Infill" : Applying Masked Language Model to Sentiment Transfer](https://mlsanity.com/paper/1908.08039/) (2019)
- [Long Text Generation by Modeling Sentence-Level and Discourse-Level Coherence](https://mlsanity.com/paper/2105.08963/) (2021)
- [A Hierarchical Neural Autoencoder for Paragraphs and Documents](https://mlsanity.com/paper/1506.01057/) (2015)
- [Structuring Latent Spaces for Stylized Response Generation](https://mlsanity.com/paper/1909.05361/) (2019)
- [SLM: Learning a Discourse Language Representation with Sentence Unshuffling](https://mlsanity.com/paper/2010.16249/) (2020)
- [Adapting Language Models for Non-Parallel Author-Stylized Rewriting](https://mlsanity.com/paper/1909.09962/) (2019)
- [Enhancing Content Preservation in Text Style Transfer Using Reverse Attention and Conditional Layer Normalization](https://mlsanity.com/paper/2108.00449/) (2021)
- [End-to-End Neural Sentence Ordering Using Pointer Network](https://mlsanity.com/paper/1611.04953/) (2016)
- [Transductive Learning for Unsupervised Text Style Transfer](https://mlsanity.com/paper/2109.07812/) (2021)
- [Guess who? Multilingual approach for the automated generation of author-stylized poetry](https://mlsanity.com/paper/1807.07147/) (2018)
- [Unsupervised Controllable Text Formalization](https://mlsanity.com/paper/1809.04556/) (2018)
- [NAST: A Non-Autoregressive Generator with Word Alignment for Unsupervised Text Style Transfer](https://mlsanity.com/paper/2106.02210/) (2021)

## Built on by (most cited first, 8 of 8)

- [How to Synthesize Text Data without Model Collapse?](https://mlsanity.com/paper/2412.14689/) (2024)
- [Collective Critics for Creative Story Generation](https://mlsanity.com/paper/2410.02428/) (2024)
- [CAT-LLM: Style-enhanced Large Language Models with Text Style Definition for Chinese Article-style Transfer](https://mlsanity.com/paper/2401.05707/) (2024)
- [Prompting Video-Language Foundation Models with Domain-specific Fine-grained Heuristics for Video Question Answering](https://mlsanity.com/paper/2410.09380/) (2024)
- [SC2: Towards Enhancing Content Preservation and Style Consistency in Long Text Style Transfer](https://mlsanity.com/paper/2406.04578/) (2024)
- [Classic4Children: Adapting Chinese Literary Classics for Children with Large Language Model](https://mlsanity.com/paper/2502.01090/) (2025)
- [Protecting Creative Writing Copyright against AI Imitation via Implicit Watermarking](https://mlsanity.com/paper/2504.00035/) (2025)
- [Coordinated incentives in AI-generated misinformation governance](https://mlsanity.com/paper/2608.07070/) (2026)

## Abstract (arXiv)

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.