Skip to content

[IJCAI'23] The official Github page of the paper "Diffusion Models for Non-autoregressive Text Generation: A Survey".

Notifications You must be signed in to change notification settings

AoiDragon/Awesome-Text-Diffusion-Models

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

8 Commits
 
 
 
 

Repository files navigation

Awesome-Text-Diffusion-Models

A collection of papers related to text diffusion models.

The organization of papers refer to our survey 'Diffusion Models for Non-autoregressive Text Generation: A Survey' , which is accepted by IJCAI 2023 survey track.

If you find our survey useful for your research, please cite the following paper:

@article{li2023diffusion,
  title={Diffusion Models for Non-autoregressive Text Generation: A Survey},
  author={Li, Yifan and Zhou, Kun and Zhao, Wayne Xin and Wen, Ji-Rong},
  journal={arXiv preprint arXiv:2303.06574},
  year={2023}
}

Continuous Text Diffusion Model

avatar

  1. Argmax Flows and Multinomial Diffusion: Learning Categorical Distributions
    Emiel Hoogeboom et al. NeurIPS 2021. [Paper]

  2. Diffusion-LM Improves Controllable Text Generation
    Xiang Lisa Li et al. NeurIPS 2022. [Paper] [Code]

  3. Composable Text Controls in Latent Space with ODEs
    Guangyi Liu et al. arxiv 2022. [Paper] [Code]

  4. DiffuSeq: Sequence to Sequence Text Generation with Diffusion Models
    Shansan Gong et al. ICLR 2023. [Paper] [Code]

  5. SSD-LM: Semi-autoregressive Simplex-based Diffusion Language Model for Text Generation and Modular Control
    Xiaochuang Han et al. arxiv 2022.[Paper] [Code]

  6. Self-conditioned Embedding Diffusion for Text Generation
    Robin Strudel et al. arxiv 2022. [Paper]

  7. Continuous diffusion for categorical data
    Sander Dieleman et al. arxiv 2022. [Paper]

  8. Difformer: Empowering Diffusion Model on Embedding Space for Text Generation
    Zhujin Gao et al. arxiv 2022. [Paper]

  9. Latent Diffusion for Language Generation
    Justin Lovelace et al. arxiv 2022. [Paper] [Code]

  10. SeqDiffuSeq: Text Diffusion with Encoder-Decoder Transformers
    Hongyi Yuan et al. arxiv 2022. [Paper] [Code]

  11. Text Generation with Diffusion Language Models: A Pre-training Approach with Continuous Paragraph Denoise
    Zhenghao Lin et al. arxiv 2022. [Paper] [Code]

  12. A Reparameterized Discrete Diffusion Model for Text Generation
    Lin Zheng et al. arxiv 2023. [Paper] [Code]

  13. DINOISER: Diffused Conditional Sequence Learning by Manipulating Noises
    Jiasheng Ye et al. arxiv 2023. [Paper] [Code]

  14. GlyphDiffusion: Text Generation as Image Generation
    Junyi Li et al. arxiv 2023. [Paper]

  15. DeTiME: Diffusion-Enhanced Topic Modeling using Encoder-decoder based LLM
    Weijie Xu et al. Findings of EMNLP 2023. [Paper]

Discrete Text Diffusion Models

2

  1. Structured Denoising Diffusion Models in Discrete State-Spaces
    Jacob Austin et al. NeurIPS 2021. [Paper]

  2. DiffusionBERT: Improving Generative Masked Language Models with Diffusion Models
    Zhengfu He et al. arXiv 2022. [Paper] [Code]

  3. Diff-Glat: Diffusion Glancing Transformer for Parallel Sequence to Sequence Learning
    Lihua Qian et al. arxiv 2022. [Paper]

  4. Diffusion-NAT: Self-Prompting Discrete Diffusion for Non-Autoregressive Text Generation
    Kun Zhou et al. arxiv 2023. [Paper]

About

[IJCAI'23] The official Github page of the paper "Diffusion Models for Non-autoregressive Text Generation: A Survey".

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published