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.
On Learning Text Style Transfer with Direct Rewards
Semi-supervised Formality Style Transfer using Language Model Discriminator and Mutual Information Maximization
TextSETTR: Few-Shot Text Style Extraction and Tunable Targeted Restyling
Cycle-Consistent Adversarial Autoencoders for Unsupervised Text Style Transfer
Unsupervised Text Style Transfer with Padded Masked Language Models
PGST: a Polyglot Gender Style Transfer method
Reflection-based Word Attribute Transfer
Multimodal Text Style Transfer for Outdoor Vision-and-Language Navigation
Improving GAN Training with Probability Ratio Clipping and Sample Reweighting
Improving Disentangled Text Representation Learning with Information-Theoretic Guidance
Stable Style Transformer: Delete and Generate Approach with Encoder-Decoder for Text Style Transfer
Parallel Data Augmentation for Formality Style Transfer
Reinforced Rewards Framework for Text Style Transfer
Learning Implicit Text Generation via Feature Matching
Review of Text Style Transfer Based on Deep Learning
Contextual Text Style Transfer
ST$^2$: Small-data Text Style Transfer via Multi-task Meta-Learning
Improve Variational Autoencoder for Text Generationwith Discrete Latent Bottleneck
Learning to Select Bi-Aspect Information for Document-Scale Text Content Manipulation
Learning to Generate Multiple Style Transfer Outputs for an Input Sentence
A Probabilistic Formulation of Unsupervised Text Style Transfer
Zero-Shot Fine-Grained Style Transfer: Leveraging Distributed Continuous Style Representations to Transfer To Unseen Styles
XL-Editor: Post-editing Sentences with XLNet
Semi-supervised Text Style Transfer: Cross Projection in Latent Space
ALTER: Auxiliary Text Rewriting Tool for Natural Language Generation
Sequence-to-sequence Pre-training with Data Augmentation for Sentence Rewriting
Transforming Delete, Retrieve, Generate Approach for Controlled Text Style Transfer
Domain Adaptive Text Style Transfer
Style Transfer for Texts: Retrain, Report Errors, Compare with Rewrites
How Sequence-to-Sequence Models Perceive Language Styles?
A Hierarchical Reinforced Sequence Operation Method for Unsupervised Text Style Transfer
Revision in Continuous Space: Unsupervised Text Style Transfer without Adversarial Learning
Educating Text Autoencoders: Latent Representation Guidance via Denoising
On Variational Learning of Controllable Representations for Text without Supervision
A Dual Reinforcement Learning Framework for Unsupervised Text Style Transfer
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.