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 126–150 of 186 papers

TitleStatusHype
Don't Take It Literally: An Edit-Invariant Sequence Loss for Text GenerationCode0
Multi-Pair Text Style Transfer on Unbalanced Data—0
A Recipe For Arbitrary Text Style Transfer with Large Language Models—0
So Different Yet So Alike! Constrained Unsupervised Text Style Transfer—0
Counterfactual Explanations for Survival Prediction of Cardiovascular ICU PatientsCode0
A Novel Estimator of Mutual Information for Learning to Disentangle Textual Representations—0
SE-DAE: Style-Enhanced Denoising Auto-Encoder for Unsupervised Text Style Transfer—0
GTAE: Graph-Transformer based Auto-Encoders for Linguistic-Constrained Text Style Transfer—0
Empirical Evaluation of Supervision Signals for Style Transfer Models—0
Parameterization of Hypercomplex Multiplications—0
An Empirical Study on Multi-Task Learning for Text Style Transfer and Paraphrase Generation—0
Rich Syntactic and Semantic Information Helps Unsupervised Text Style Transfer—0
DGST: a Dual-Generator Network for Text Style Transfer—0
On Learning Text Style Transfer with Direct RewardsCode0
Semi-supervised Formality Style Transfer using Language Model Discriminator and Mutual Information MaximizationCode0
Cycle-Consistent Adversarial Autoencoders for Unsupervised Text Style Transfer—0
Unsupervised Text Style Transfer with Padded Masked Language Models—0
TextSETTR: Label-Free Text Style Extraction and Tunable Targeted Restyling—0
PGST: a Polyglot Gender Style Transfer methodCode0
Story-level Text Style Transfer: A Proposal—0
Improving Disentangled Text Representation Learning with Information-Theoretic Guidance—0
Reinforced Rewards Framework for Text Style Transfer—0
Learning Implicit Text Generation via Feature Matching—0
Review of Text Style Transfer Based on Deep Learning—0
Contextual Text Style Transfer—0
Show:102550
← PrevPage 6 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