SOTAVerified

Text Style Transfer

Text Style Transfer is the task of controlling certain attributes of generated text. The state-of-the-art methods can be categorized into two main types which are used on parallel and non-parallel data. Methods on parallel data are typically supervised methods that use a neural sequence-to-sequence model with the encoder-decoder architecture. Methods on non-parallel data are usually unsupervised approaches using Disentanglement, Prototype Editing and Pseudo-Parallel Corpus Construction.

The popular benchmark for this task is the Yelp Review Dataset. Models are typically evaluated with the metrics of Sentiment Accuracy, BLEU, and PPL.

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 101–150 of 186 papers

TitleStatusHype
Review of Text Style Transfer Based on Deep Learning—0
Rich Syntactic and Semantic Information Helps Unsupervised Text Style Transfer—0
SE-DAE: Style-Enhanced Denoising Auto-Encoder for Unsupervised Text Style Transfer—0
Semi-supervised Text Style Transfer: Cross Projection in Latent Space—0
SentiInc: Incorporating Sentiment Information into Sentiment Transfer Without Parallel Data—0
SETTP: Style Extraction and Tunable Inference via Dual-level Transferable Prompt Learning—0
SimpleStyle: An Adaptable Style Transfer Approach—0
So Different Yet So Alike! Constrained Unsupervised Text Style Transfer—0
ST^2: Small-data Text Style Transfer via Multi-task Meta-Learning—0
Story-level Text Style Transfer: A Proposal—0
StyleFlow: Disentangle Latent Representations via Normalizing Flow for Unsupervised Text Style Transfer—0
Syntax Matters! Syntax-Controlled in Text Style Transfer—0
TD-ConE: An Information-Theoretic Approach to Assessing Parallel Text Generation Data—0
TextSETTR: Label-Free Text Style Extraction and Tunable Targeted Restyling—0
Text Style Transfer: An Introductory Overview—0
Text Style Transfer Evaluation Using Large Language Models—0
Text Style Transfer for Bias Mitigation using Masked Language Modeling—0
Text Style Transfer: Leveraging a Style Classifier on Entangled Latent Representations—0
Text Style Transfer via Optimal Transport—0
Text Style Transfer with Confounders—0
``Transforming'' Delete, Retrieve, Generate Approach for Controlled Text Style Transfer—0
T-STAR: Truthful Style Transfer using AMR Graph as Intermediate Representation—0
Typography With Decor: Intelligent Text Style Transfer—0
Unsupervised Text Style Transfer via LLMs and Attention Masking with Multi-way Interactions—0
Unsupervised Text Style Transfer with Content Embeddings—0
Unsupervised Text Style Transfer with Deep Generative Models—0
Unsupervised Text Style Transfer with Padded Masked Language Models—0
XL-Editor: Post-editing Sentences with XLNet—0
On Variational Learning of Controllable Representations for Text without SupervisionCode0
Unsupervised Text Style Transfer using Language Models as DiscriminatorsCode0
ALTER: Auxiliary Text Rewriting Tool for Natural Language GenerationCode0
VAE based Text Style Transfer with Pivot Words Enhancement LearningCode0
Controllable Artistic Text Style Transfer via Shape-Matching GANCode0
Don’t Take It Literally: An Edit-Invariant Sequence Loss for Text GenerationCode0
Specializing Small Language Models towards Complex Style Transfer via Latent Attribute Pre-TrainingCode0
Towards Robust and Semantically Organised Latent Representations for Unsupervised Text Style TransferCode0
Don't Take It Literally: An Edit-Invariant Sequence Loss for Text GenerationCode0
STEER: Unified Style Transfer with Expert ReinforcementCode0
Collaborative Learning of Bidirectional Decoders for Unsupervised Text Style TransferCode0
Don't lose the message while paraphrasing: A study on content preserving style transferCode0
Learning Sentiment Memories for Sentiment Modification without Parallel DataCode0
Learning to Select Bi-Aspect Information for Document-Scale Text Content ManipulationCode0
Learning from Bootstrapping and Stepwise Reinforcement Reward: A Semi-Supervised Framework for Text Style TransferCode0
Structured Content Preservation for Unsupervised Text Style TransferCode0
Studying the role of named entities for content preservation in text style transferCode0
Are Large Language Models Actually Good at Text Style Transfer?Code0
Learning Evaluation Models from Large Language Models for Sequence GenerationCode0
MSSRNet: Manipulating Sequential Style Representation for Unsupervised Text Style TransferCode0
Domain Adaptive Text Style TransferCode0
Multidimensional Evaluation for Text Style Transfer Using ChatGPTCode0
Show:102550
← PrevPage 3 of 4Next →
All datasetsYelp Review Dataset (Small)Yelp Review Dataset (Large)

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1SAE+DiscriminatorG-Score (BLEU, Accuracy)74.56—Unverified
2LatentOps (Few shot)G-Score (BLEU, Accuracy)71.6—Unverified
3SentiIncG-Score (BLEU, Accuracy)66.25—Unverified
4DeleteAndRetrieveG-Score (BLEU, Accuracy)54.64—Unverified
5DeleteOnlyG-Score (BLEU, Accuracy)54.11—Unverified
6MultiDecoderG-Score (BLEU, Accuracy)45.02—Unverified
7CAEG-Score (BLEU, Accuracy)38.66—Unverified
8StyleEmbeddingG-Score (BLEU, Accuracy)31.31—Unverified
#ModelMetricClaimedVerifiedStatus
1SentiIncG-Score (BLEU, Accuracy)59.17—Unverified
2StyleEmbBLEU30—Unverified