SSD-LM: Semi-autoregressive Simplex-based Diffusion Language Model for Text Generation and Modular Control
Abstract
Despite the growing success of diffusion models in continuous-valued domains (e.g., images), similar efforts for discrete domains such as text have yet to match the performance of autoregressive language models. In this work, we present SSD-LM—a diffusion-based language model with two key design choices. First, SSD-LM is semi-autoregressive, iteratively generating blocks of text, allowing for flexible output length at decoding time while enabling local bidirectional context updates. Second, it is simplex-based, performing diffusion on the natural vocabulary space rather than a learned latent space, allowing us to incorporate classifier guidance and modular control using off-the-shelf classifiers without any adaptation. We evaluate SSD-LM on unconstrained text generation benchmarks, and show that it matches or outperforms strong autoregressive GPT-2 models across standard quality and diversity metrics, while vastly outperforming diffusion-based baselines. On controlled text generation, SSD-LM also outperforms competitive baselines, with an extra advantage in modularity.- Anthology ID:
- 2023.acl-long.647
- Volume:
- Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
- Month:
- July
- Year:
- 2023
- Address:
- Toronto, Canada
- Editors:
- Anna Rogers, Jordan Boyd-Graber, Naoaki Okazaki
- Venue:
- ACL
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 11575–11596
- Language:
- URL:
- https://aclanthology.org/2023.acl-long.647
- DOI:
- 10.18653/v1/2023.acl-long.647
- Cite (ACL):
- Xiaochuang Han, Sachin Kumar, and Yulia Tsvetkov. 2023. SSD-LM: Semi-autoregressive Simplex-based Diffusion Language Model for Text Generation and Modular Control. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 11575–11596, Toronto, Canada. Association for Computational Linguistics.
- Cite (Informal):
- SSD-LM: Semi-autoregressive Simplex-based Diffusion Language Model for Text Generation and Modular Control (Han et al., ACL 2023)
- PDF:
- https://preview.aclanthology.org/teach-a-man-to-fish/2023.acl-long.647.pdf