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
TD-ConE: An Information-Theoretic Approach to Assessing Parallel Text Generation Data—0
BTS: A Bi-Lingual Benchmark for Text Segmentation in the Wild—0
VAE based Text Style Transfer with Pivot Words Enhancement LearningCode0
Multilingual pre-training with Language and Task Adaptation for Multilingual Text Style Transfer—0
DAML-ST5: Low Resource Style Transfer via Domain Adaptive Meta Learning—0
Collaborative Learning of Bidirectional Decoders for Unsupervised Text Style TransferCode0
Rethinking Sentiment Style Transfer—0
Exploring Non-Autoregressive Text Style TransferCode0
Emotion Style Transfer with a Specified Intensity Using Deep Reinforcement Learning—0
Enhance Long Text Understanding via Distilled Gist Detector from Abstractive Summarization—0
Self-Supervised Knowledge Assimilation for Expert-Layman Text Style TransferCode0
A Review of Text Style Transfer using Deep Learning—0
Text Style Transfer with Confounders—0
Preventing Author Profiling through Zero-Shot Multilingual Back-TranslationCode0
Disentangling Generative Factors in Natural Language with Discrete Variational Autoencoders—0
A Recipe For Arbitrary Text Style Transfer with Large Language Models—0
Unsupervised Text Style Transfer with Content Embeddings—0
Contextualizing Variation in Text Style Transfer Datasets—0
Syntax Matters! Syntax-Controlled in Text Style Transfer—0
Text Style Transfer: Leveraging a Style Classifier on Entangled Latent Representations—0
A Hierarchical VAE for Calibrating Attributes while Generating Text using Normalizing Flow—0
Multi-Pair Text Style Transfer for Unbalanced Data via Task-Adaptive Meta-Learning—0
Enhancing Content Preservation in Text Style Transfer Using Reverse Attention and Conditional Layer NormalizationCode0
基于风格化嵌入的中文文本风格迁移(Chinese text style transfer based on stylized embedding)—0
Counterfactuals to Control Latent Disentangled Text Representations for Style Transfer—0
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 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