DiffusionBERT: Improving Generative Masked Language Models with Diffusion Models
Zhengfu He, Tianxiang Sun, Qiong Tang, Kuanning Wang, Xuanjing Huang, Xipeng Qiu
Abstract
We present DiffusionBERT, a new generative masked language model based on discrete dif- fusion models. Diffusion models and many pre- trained language models have a shared training objective, i.e., denoising, making it possible to combine the two powerful models and enjoy the best of both worlds. On the one hand, dif- fusion models offer a promising training strat- egy that helps improve the generation quality. On the other hand, pre-trained denoising lan- guage models (e.g., BERT) can be used as a good initialization that accelerates convergence. We explore training BERT to learn the reverse process of a discrete diffusion process with an absorbing state and elucidate several designs to improve it. First, we propose a new noise schedule for the forward diffusion process that controls the degree of noise added at each step based on the information of each token. Sec- ond, we investigate several designs of incorpo- rating the time step into BERT. Experiments on unconditional text generation demonstrate that DiffusionBERT achieves significant improve- ment over existing diffusion models for text (e.g., D3PM and Diffusion-LM) and previous generative masked language models in terms of perplexity and BLEU score. Promising re- sults in conditional generation tasks show that DiffusionBERT can generate texts of compa- rable quality and more diverse than a series of established baselines.- Anthology ID:
- 2023.acl-long.248
- Volume:
- Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
- Month:
- July
- Year:
- 2023
- Address:
- Toronto, Canada
- Venue:
- ACL
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 4521–4534
- Language:
- URL:
- https://aclanthology.org/2023.acl-long.248
- DOI:
- 10.18653/v1/2023.acl-long.248
- Cite (ACL):
- Zhengfu He, Tianxiang Sun, Qiong Tang, Kuanning Wang, Xuanjing Huang, and Xipeng Qiu. 2023. DiffusionBERT: Improving Generative Masked Language Models with Diffusion Models. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 4521–4534, Toronto, Canada. Association for Computational Linguistics.
- Cite (Informal):
- DiffusionBERT: Improving Generative Masked Language Models with Diffusion Models (He et al., ACL 2023)
- PDF:
- https://preview.aclanthology.org/remove-xml-comments/2023.acl-long.248.pdf