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.
Controllable Artistic Text Style Transfer via Shape-Matching GAN
Grammatical Error Correction and Style Transfer via Zero-shot Monolingual Translation
Reinforcement Learning Based Text Style Transfer without Parallel Training Corpus
Formality Style Transfer with Hybrid Textual Annotations
IMaT: Unsupervised Text Attribute Transfer via Iterative Matching and Translation
Multiple-Attribute Text Style Transfer
Structured Content Preservation for Unsupervised Text Style Transfer
Learning Sentiment Memories for Sentiment Modification without Parallel Data
Disentangled Representation Learning for Non-Parallel Text Style Transfer
Unsupervised Text Style Transfer using Language Models as Discriminators
Fighting Offensive Language on Social Media with Unsupervised Text Style Transfer
Unpaired Sentiment-to-Sentiment Translation: A Cycled Reinforcement Learning Approach
Style Transfer Through Back-Translation
QuaSE: Accurate Text Style Transfer under Quantifiable Guidance
Delete, Retrieve, Generate: A Simple Approach to Sentiment and Style Transfer
Dear Sir or Madam, May I introduce the GYAFC Dataset: Corpus, Benchmarks and Metrics for Formality Style Transfer
Style Transfer in Text: Exploration and Evaluation
Style Transfer from Non-Parallel Text by Cross-Alignment
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.