A Paper List for Style Transfer in Text

This is a paper list for style transfer in text. It also contains some related research areas, including controlled text generation.

Keyword: Style Transfer, Unsupervised, Natural Language Processing

Paper List

Review

• Deep Learning for Text Style Transfer: A Survey, arXiv, 2020, [paper]
• Text Style Transfer: A Review and Experiment Evaluation, arXiv, 2020, [paper]
• A Review of Text Style Transfer using Deep Learning, TAI, 2021, [paper]

Dataset

• Dear Sir or Madam, May I introduce the YAFC Corpus: Corpus, Benchmarks and Metrics for Formality Style Transfer, NAACL-HLT 2018, [paper]
• A Dataset for Low-Resource Stylized Sequence-to-Sequence Generation, AAAI, 2020, [paper], [code]
• APPDIA: A Discourse-aware Transformer-based Style Transfer Model for Offensive Social Media Conversations, COLING 2022, [paper]
• ParaDetox: Detoxification with Parallel Data, ACL 2022, [paper]

Supervised (Parallel Data)

• Shakespearizing Modern Language Using Copy-Enriched Sequence to Sequence Models, EMNLP-2017 Workshop, [paper][code]
• Evaluating prose style transfer with the Bible, 2018, [paper]
• Harnessing Pre-Trained Neural Networks with Rules for Formality Style Transfer, EMNLP-2019, [paper], [code]
• Automatically Neutralizing Subjective Bias in Text, AAAI, 2020, [paper]
• Formality Style Transfer with Shared Latent Space, COLING 2020, [paper]
• Smells like Teen Spirit:An Exploration of Sensorial Style in Literary Genres, COLING 2022, [paper]
• ParaDetox: Detoxification with Parallel Data, ACL 2022, [paper]

Unsupervised (Non-parallel Data)

• Sequence to Better Sequence: Continuous Revision of Combinatorial Structures, ICML-2017, [paper], [code]
• Toward Controlled Generation of Text, ICML-2017, [paper], [official code], [unofficial code]
• Style Transfer from Non-Parallel Text by Cross-Alignment, NIPS-2017, [paper], [code]
• Adversarially Regularized Autoencoders, ICML-2018, [paper], [code]
• Zero-Shot Style Transfer in Text Using Recurrent Neural Networks, Arxiv-2017, [paper], [code]
• Style Transfer in Text: Exploration and Evaluation, AAAI-2018, [paper], [code]
• Delete, Retrieve, Generate: A Simple Approach to Sentiment and Style Transfer, NAACL-2018, [paper], [code]
• SHAPED: Shared-Private Encoder-Decoder for Text Style Adaptation, NAACL-2018, [paper]
• Sentiment Transfer using Seq2Seq Adversarial Autoencoders, project for CSYE7245 Northeastern University, [paper]
• Style Transfer Through Back-Translation, ACL-2018, [paper], [code]
• Unpaired Sentiment-to-Sentiment Translation: A Cycled Reinforcement Learning Approach, ACL-2018, [paper], [code]
• Fighting Offensive Language on Social Media with Unsupervised Text Style Transfer, ACL-2018, [paper]
• Unsupervised Text Style Transfer using Language Models as Discriminators, NIPS-2018, [paper]
• Disentangled Representation Learning for Non-Parallel Text Style Transfer, ACL-2019, [paper], [code]
• Language Style Transfer from Sentences with Arbitrary Unknown Styles, Arxiv, [paper]
• Style Transfer as Unsupervised Machine Translation, Arxiv, [paper]
• Learning Sentiment Memories for Sentiment Modification without Parallel Data, EMNLP-2018, [paper], [code]
• Style Transfer Through Multilingual and Feedback-Based Back-Translation, Arxiv, 2018, [paper]
• Structured Content Preservation for Unsupervised Text Style Transfer, OpenReview, 2018, [paper]
• Unsupervised Controllable Text Formalization, AAAI, 2019, [paper], [code]
• Large-scale Hierarchical Alignment for Data-driven Text Rewriting, RANLP, 2019, [paper]
• Learning Criteria and Evaluation Metrics for Textual Transfer between Non-Parallel Corpora, Arxiv, 2018, [paper]
• Content preserving text generation with attribute controls, NIPS, 2018, [paper]
• QuaSE: Sequence Editing under Quantifiable Guidance, EMNLP, 2018, [paper]
• Adversarial Text Generation via Feature-Mover's Distance, NeurIPS, 2018, [paper], [unofficial code]
• Towards Controlled Transformation of Sentiment in Sentences, ICAART, 2019, [paper]
• Formality Style Transfer with Hybrid Textual Annotations, Arxiv, 2019, [paper]
• Reinforcement Learning Based Text Style Transfer without Parallel Training Corpus, NAACL-2019, 2019, [paper]
• Grammatical Error Correction and Style Transfer via Zero-shot Monolingual Translation, Arxiv, 2019, [paper]
• Multiple-Attribute Text Style Transfer (Rewriting), ICLR, 2019, [paper]
• Style Transformer: Unpaired Text Style Transfer without Disentangled Latent Representation, ACL, 2019, [paper]
• A Dual Reinforcement Learning Framework for Unsupervised Text Style Transfer, IJCAI, 2019, [paper], [code]
• On Variational Learning of Controllable Representations for Text without Supervision, ICML, 2020, [paper]
• Revision in Continuous Space: Fine-Grained Control of Text Style Transfer, AAAI, 2020, [paper]
• Controllable Unsupervised Text Attribute Transfer via Editing Entangled Latent Representation, NIPS, 2019, [paper], [code]
• Disentangled Representation Learning for Non-Parallel Text Style Transfer, ACL, 2019, [paper], [code]
• A Hierarchical Reinforced Sequence Operation Method for Unsupervised Text Style Transfer, ACL, 2019, [paper], [code]
• Unsupervised Text Attribute Transfer via Iterative Matching and Translation, EMNLP, 2019, [paper]
• Mask and Infill: Applying Masked Language Model to Sentiment Transfer, IJCAI, 2019, [paper]
• Transforming Delete, Retrieve, Generate Approach for Controlled Text Style Transfer, EMNLP, 2019, [paper], [code]
• Domain Adaptive Text Style Transfer, EMNLP, 2019, [paper], [code]
• Style Transfer for Texts: Retrain, Report Errors, Compare with Rewrites, EMNLP, 2019, [paper], [code]
• Decomposing Textual Information For Style Transfer, WNGT, 2019, [paper]
• Zero-Shot Fine-Grained Style Transfer: Leveraging Distributed Continuous Style Representations to Transfer To Unseen Styles, Arxiv, 2019, [paper]
• A Probabilistic Formulation of Unsupervised Text Style Transfer, ICLR, 2020, [paper], [code]
• Generating sentences from disentangled syntactic and semantic spaces, ACL, 2019, [paper], [code]
• SentiInc: Incorporating Sentiment Information into Sentiment Transfer Without Parallel Data, ECIR, 2020, [paper]
• Expertise Style Transfer: A New Task Towards Better Communication between Experts and Laymen, ACL, 2020, [paper]
• Contextual Text Style Transfer, Arxiv, 2020, [paper]
• Exploring Contextual Word-level Style Relevance for Unsupervised Style Transfer, ACL, 2020, [paper]
• ST$^2$: Small-data Text Style Transfer via Multi-task Meta-Learning, Arxiv, 2020, [paper]
• Reinforced Rewards Framework for Text Style Transfer, ECIR, 2020, [paper]
• Challenges in Emotion Style Transfer: An Exploration with a Lexical Substitution Pipeline, SocialNLP, ACL, 2020, [paper]
• Stable Style Transformer: Delete and Generate Approach with Encoder-Decoder for Text Style Transfer, Arxiv, 2020, [paper]
• Unsupervised Automatic Text Style Transfer Using LSTM, NLPCC, 2017, [paper]
• Text Style Transfer via Learning Style Instance Supported Latent Space, IJCAI, 2020, [paper]
• Learning to Generate Multiple Style Transfer Outputs for an Input Sentence, Arxiv, 2020, [paper]
• Pre-train and Plug-in: Flexible Conditional Text Generation with Variational Auto-Encoders, ACL, 2020, [paper]
• Unsupervised Text Style Transfer with Padded Masked Language Models, EMNLP, 2020, [paper]
• Reformulating Unsupervised Style Transfer as Paraphrase Generation, EMNLP 2020, [paper]
• Plug and Play Autoencoders for Conditional Text Generation, EMNLP 2020 [paper]
• DGST: a Dual-Generator Network for Text Style Transfer, EMNLP 2020, [paper]
• How Positive Are You: Text Style Transfer Using Adaptive Style Embedding, EMNLP 2020, [paper]
• Unsupervised Text Generation by Learning from Search, NeurIPS 2020, [paper]
• Cycle-Consistent Adversarial Autoencoders for Unsupervised Text Style Transfer, COLING 2020, [paper]
• TextSETTR: Label-Free Text Style Extraction and Tunable Targeted Restyling, Arxiv, 2020, [paper]
• Non-parallel text style transfer with domain adaptation and an attention model, Applied Intelligence, 2021, [paper], [code]
• Exploring Non-Autoregressive Text Style Transfer, EMNLP, 2021, [paper]
• Generic resources are what you need: Style transfer tasks without task-specific parallel training data, EMNLP, 2021, [paper]
• Style Pooling: Automatic Text Style Obfuscation for Improved Classification Fairness, EMNLP, 2021, [paper]
• Transductive Learning for Unsupervised Text Style Transfer, EMNLP, 2021, [paper]
• Collaborative Learning of Bidirectional Decoders for Unsupervised Text Style Transfer, EMNLP, 2021, [paper]
• On Learning Text Style Transfer with Direct Rewards, NAACL, 2021, [paper]
• STYLEPTB: A Compositional Benchmark for Fine-grained Controllable Text Style Transfer, NAACL, 2021, [paper],[code]
• Multi-Style Transfer with Discriminative Feedback on Disjoint Corpus, NAACL, 2021, [paper]
• Civil Rephrases Of Toxic Texts With Self-Supervised Transformers, EACL, 2021, [paper], [code]
• Efficient Reinforcement Learning for Unsupervised Controlled Text Generation, Arxiv, 2022, [paper]
• So Different Yet So Alike! Constrained Unsupervised Text Style Transfer, ACL, 2022, [paper], [code]

Semi-supervised

• Semi-supervised Text Style Transfer: Cross Projection in Latent Space, EMNLP, 2019, [paper]
• Parallel Data Augmentation for Formality Style Transfer, ACL, 2020, [paper]
• Semi-Supervised Formality Style Transfer with Consistency Training, ACL, 2022, [paper], [code]

Evaluation and Analysis

• Evaluating Style Transfer for Text, NAACL, 2019, [paper1], [paper2]
• Rethinking Text Attribute Transfer: A Lexical Analysis, INLG, 2019, [paper], [code]
• Unsupervised Evaluation Metrics and Learning Criteria for Non-Parallel Textual Transfer, EMNLP Workshop on Neural Generation and Translation (WNGT), 2019, [paper]
• The Daunting Task of Real-World Textual Style Transfer Auto-Evaluation, WNGT, 2019, [paper]
• Style-transfer and Paraphrase: Looking for a Sensible Semantic Similarity Metric, Arxiv, 2020, [paper]
• What is wrong with style transfer for texts? Arxiv, [paper]
• Style versus Content: A distinction without a (learnable) difference?, COLING 2020, [paper]
• Rethinking Sentiment Style Transfer, EMNLP 2021, [paper]
• Evaluating the Evaluation Metrics for Style Transfer: A Case Study in Multilingual Formality Transfer, EMNLP 2021, [paper]
• Does It Capture STEL? A Modular, Similarity-based Linguistic Style Evaluation Framework, EMNLP 2021, [paper]

Stylistic Related Papers

• Controlling Politeness in Neural Machine Translation via Side Constraints, NAACL 2016, [paper]
• A Study of Style in Machine Translation: Controlling the Formality of Machine Translation Output, EMNLP 2017, [paper]
• Controlling Linguistic Style Aspects in Neural Language Generation, EMNLP-2017 Workshop, [paper]
• Is writing style predictive of scientific fraud?, EMNLP-2017 Workshop, [paper]
• Incorporating Pseudo-Parallel Data for Quantifiable Sequence Editing, EMNLP-2018, [paper]
• Polite Dialogue Generation Without Parallel Data, TACL, [paper]
• Adversarial Decomposition of Text Representation, Arxiv, [paper]
• Unsupervised Stylish Image Description Generation via Domain Layer Norm, AAAI 2019, [paper]
• Transfer Learning for Style-Specific Text Generation, UNK, 2018, [paper]
• Generating lyrics with variational autoencoder and multi-modal artist embeddings, Arxiv, 2018, [paper]
• Generating Sentences by Editing Prototypes, TACL, 2018, [paper]
• ALTER: Auxiliary Text Rewriting Tool for Natural Language Generation, EMNLP, 2019, [paper]
• Stylized Text Generation Using Wasserstein Autoencoders with a Mixture of Gaussian Prior, Arxiv, 2019, [paper]
• Adapting Language Models for Non-Parallel Author-Stylized Rewriting, AAAI, 2020 [paper]
• Structuring Latent Spaces for Stylized Response Generation, EMNLP, 2019, [paper]
• Complementary Auxiliary Classifiers for Label-Conditional Text Generation, AAAI, 2020, [paper], [code]
• Hooks in the Headline: Learning to Generate Headlines with Controlled Styles, ACL, 2020, [paper]
• Exploring Contextual Word-level Style Relevance for Unsupervised Style Transfer, ACL, 2020, [paper]
• Parallel Data Augmentation for Formality Style Transfer, ACL, 2020, [paper]
• Politeness Transfer: A Tag and Generate Approach, ACL, 2020, [paper]
• Towards A Friendly Online Community: An Unsupervised Style Transfer Framework for Profanity Redaction, COLING 2020, [paper]
• Generating similes effortlessly like a Pro: A Style Transfer Approach for Simile Generation, EMNLP 2020, [paper]
• PowerTransformer: Unsupervised Controllable Revision for Biased Language Correction, EMNLP 2020, [paper]
• Does BERT Learn as Humans Perceive? Understanding Linguistic Styles through Lexica, EMNLP 2021, [paper]

Controlled Text Generation (Similar, but not exactly style transfer)

• Toward Controlled Generation of Text, ICML 2017. [paper]
• CTRL: A Conditional Transformer Language Model for Controllable Generation, arXiv 2019. [paper]
• Defending Against Neural Fake News, NeurIPS 2019. (about conditional generation of neural fake news) [paper]
• Plug and Play Language Models: A Simple Approach to Controlled Text Generation, ICLR 2020. [paper]
• COCON: A Self-Supervised Approach for Controlled Text Generation, ICLR 2021. [paper]
• MISS: An Assistant for Multi-Style Simultaneous Translation, EMNLP, 2021. [paper]

Unsupervised Seq2Seq

• Unsupervised neural machine translation, 2017. [paper]

Workshop and Tutorial

• Stylistic Variation, EMNLP-2017, [link]
• Stylistic Variation, NAACL-HLT-2018, [link]
• Stylized Text Generation, ACL-2020, [link] [video-part1] [video-part2]

Copyright

By Zhenxin Fu ([email protected]) from Peking University.
Welcome to open an issue or make a pull request!