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 51–75 of 186 papers

TitleStatusHype
Replacing Language Model for Style TransferCode0
On Text Style Transfer via Style Masked Language Models—0
StoryTrans: Non-Parallel Story Author-Style Transfer with Discourse Representations and Content EnhancingCode1
Composable Text Controls in Latent Space with ODEsCode1
GenText: Unsupervised Artistic Text Generation via Decoupled Font and Texture Manipulation—0
Text Style Transfer via Optimal Transport—0
Don’t Take It Literally: An Edit-Invariant Sequence Loss for Text GenerationCode0
Studying the role of named entities for content preservation in text style transferCode0
RLPrompt: Optimizing Discrete Text Prompts with Reinforcement LearningCode2
Low Resource Style Transfer via Domain Adaptive Meta Learning—0
Learning to Model Editing ProcessesCode1
Learning from Bootstrapping and Stepwise Reinforcement Reward: A Semi-Supervised Framework for Text Style TransferCode0
So Different Yet So Alike! Constrained Unsupervised Text Style TransferCode1
Towards Robust and Semantically Organised Latent Representations for Unsupervised Text Style TransferCode0
A large-scale computational study of content preservation measures for text style transfer and paraphrase generationCode1
A Study on Manual and Automatic Evaluation for Text Style Transfer: The Case of Detoxification—0
A Survey on Non-Autoregressive Generation for Neural Machine Translation and BeyondCode1
Non-Parallel Text Style Transfer with Self-Parallel SupervisionCode0
Efficient Reinforcement Learning for Unsupervised Controlled Text Generation—0
Human Judgement as a Compass to Navigate Automatic Metrics for Formality TransferCode0
Inducing Positive Perspectives with Text ReframingCode1
Diverse Text Generation via Variational Encoder-Decoder Models with Gaussian Process PriorsCode1
Multilingual Pre-training with Language and Task Adaptation for Multilingual Text Style TransferCode0
IT5: Text-to-text Pretraining for Italian Language Understanding and GenerationCode1
Variational Autoencoder with Disentanglement Priors for Low-Resource Task-Specific Natural Language GenerationCode0
Show:102550
← PrevPage 3 of 8Next →
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