Text Style Transfer
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 3
- 평가표
- 2
- 보존된 평가 기록
- 10
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.
논문
이 태스크와 하위 분야의 관련 논문입니다. 실제 성능 비교는 평가 결과에서 확인하세요.
MSSRNet: Manipulating Sequential Style Representation for Unsupervised Text Style Transfer
Identifying the style by a qualified reader on a short fragment of generated poetry
Text Style Transfer Back-Translation
A Call for Standardization and Validation of Text Style Transfer Evaluation
Fine-grained Text Style Transfer with Diffusion-Based Language Models
Balancing Effect of Training Dataset Distribution of Multiple Styles for Multi-Style Text Transfer
Reducing Sequence Length by Predicting Edit Operations with Large Language Models
CoEdIT: Text Editing by Task-Specific Instruction Tuning
Adapter-TST: A Parameter Efficient Method for Multiple-Attribute Text Style Transfer
Multidimensional Evaluation for Text Style Transfer Using ChatGPT
Conversation Style Transfer using Few-Shot Learning
Prompt-Based Editing for Text Style Transfer
Pay Attention to Your Tone: Introducing a New Dataset for Polite Language Rewrite
SimpleStyle: An Adaptable Style Transfer Approach
StyleFlow: Disentangle Latent Representations via Normalizing Flow for Unsupervised Text Style Transfer
T-STAR: Truthful Style Transfer using AMR Graph as Intermediate Representation
Replacing Language Model for Style Transfer
On Text Style Transfer via Style Masked Language Models
StoryTrans: Non-Parallel Story Author-Style Transfer with Discourse Representations and Content Enhancing
Composable Text Controls in Latent Space with ODEs
GenText: Unsupervised Artistic Text Generation via Decoupled Font and Texture Manipulation
Studying the role of named entities for content preservation in text style transfer
Low Resource Style Transfer via Domain Adaptive Meta Learning
RLPrompt: Optimizing Discrete Text Prompts with Reinforcement Learning
Learning to Model Editing Processes
Learning from Bootstrapping and Stepwise Reinforcement Reward: A Semi-Supervised Framework for Text Style Transfer
So Different Yet So Alike! Constrained Unsupervised Text Style Transfer
Towards Robust and Semantically Organised Latent Representations for Unsupervised Text Style Transfer
A Survey on Non-Autoregressive Generation for Neural Machine Translation and Beyond
Non-Parallel Text Style Transfer with Self-Parallel Supervision
Efficient Reinforcement Learning for Unsupervised Controlled Text Generation
Human Judgement as a Compass to Navigate Automatic Metrics for Formality Transfer
Inducing Positive Perspectives with Text Reframing
Diverse Text Generation via Variational Encoder-Decoder Models with Gaussian Process Priors
Semi-Supervised Formality Style Transfer with Consistency Training
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.