Abstract
Though existing researches have achieved impressive results in controlled text generation, they focus mainly on single-attribute control. However, in applications like automatic comments, the topic and sentiment need to be controlled simultaneously. In this work, we propose a new framework for multi-attribute controlled text generation. To achieve this, we design a contrastive-generator that can effectively generate texts with more attributes. In order to increase the convergence of the text on the desired attributes, we adopt an external-discriminator to distinguish whether the generated text holds the desired attributes. Moreover, we propose top-n weighted decoding to further improve the relevance of texts to attributes. Automated evaluations and human evaluations show that our framework achieves remarkable controllability in multi-attribute generation while keeping the text fluent and diverse. It also yields promising performance on zero-shot generation.- Anthology ID:
- 2022.coling-1.516
- Volume:
- Proceedings of the 29th International Conference on Computational Linguistics
- Month:
- October
- Year:
- 2022
- Address:
- Gyeongju, Republic of Korea
- Venue:
- COLING
- SIG:
- Publisher:
- International Committee on Computational Linguistics
- Note:
- Pages:
- 5904–5913
- Language:
- URL:
- https://aclanthology.org/2022.coling-1.516
- DOI:
- Cite (ACL):
- Guisheng Liu, Yi Li, Yanqing Guo, Xiangyang Luo, and Bo Wang. 2022. Multi-Attribute Controlled Text Generation with Contrastive-Generator and External-Discriminator. In Proceedings of the 29th International Conference on Computational Linguistics, pages 5904–5913, Gyeongju, Republic of Korea. International Committee on Computational Linguistics.
- Cite (Informal):
- Multi-Attribute Controlled Text Generation with Contrastive-Generator and External-Discriminator (Liu et al., COLING 2022)
- PDF:
- https://preview.aclanthology.org/remove-xml-comments/2022.coling-1.516.pdf
- Data
- IMDb Movie Reviews