text-style-transfer 话题在 GitHub 上没有填写简介，这里按 Star 数汇总最相关的热门仓库。
A Neural Language Style Transfer framework to transfer natural language text smoothly between fine-grained language styles like formal/casual, active/passive, and many more. Created by Prithiviraj Damodaran. Open to pull requests and other forms of collaboration.
StyleLLM文风大模型：基于大语言模型的文本风格迁移项目。 Text style transfer base on Large Language Model. #文字修饰 # 润色 #风格模仿
A Dual Reinforcement Learning Framework for Unsupervised Text Style Transfer (IJCAI 2019)
Code for "Controllable Unsupervised Text Attribute Transfer via Editing Entangled Latent Representation" (NeurIPS 2019)
[EMNLP 2023] Composable text generation & editing by ODE sampling in the latent space of a pretrained-LM VAE — compose sentiment, tense, formality, keyword controls without retraining
Implementation of "Disentangled Representation Learning for Non-Parallel Text Style Transfer(ACL 2019)" in Pytorch
A list of resources about Text Style Transfer
Text style transfer benchmark
The source code of Text Style Transfer via Learning Style Instance Supported Latent Space (IJCAI 2020).
Implementation of CycleGAN for Text style transfer with PyTorch.
Thank you BART! Rewarding Pre-Trained Models Improves Formality Style Transfer (ACL 2021)
金庸和古龙之间的文本风格转换
Interpretable stylometric profiling + author-style transfer built on explicit and LLM-genenated JSON fingerprints and local measurements. Fingerprint your corpus, inspect/visualize signals, then LLM-generate stylistically similar text with meaning preserved, deterministic post-processing, normalization controls, and deviation reports. CLI + API.
Style transfer in text using cycle-consistent WGANs
Implementation of INLG 19 paper: Rethinking Text Attribute Transfer: A Lexical Analysis
Code for "Data-to-text Generation with Style Imitation." [Findings of EMNLP 2020]
Repository for author masking
About, prompt-based few-shot learning, Text Generation with Prompting
A neural text style transfer model
This repository contains the code for the paper "Self-supervised Text Style Transfer using Cycle-Consistent Adversarial Networks".