DisCup: Discriminator Cooperative Unlikelihood Prompt-tuning for Controllable Text Generation

Hanqing Zhang, Dawei Song


Abstract
Prompt learning with immensely large Casual Language Models (CLMs) has been shown promising for attribute-controllable text generation (CTG). However, vanilla prompt tuning tends to imitate training corpus characteristics beyond the control attributes, resulting in a poor generalization ability. Moreover, it is less able to capture the relationship between different attributes, further limiting the control performance. In this paper, we propose a new CTG approach, namely DisCup, which incorporates the attribute knowledge of discriminator to optimize the control-prompts, steering a frozen CLM to produce attribute-specific texts. Specifically, the frozen CLM model, capable of producing multitudinous texts, is first used to generate the next-token candidates based on the context, so as to ensure the diversity of tokens to be predicted. Then, we leverage an attribute-discriminator to select desired/undesired tokens from those candidates, providing the inter-attribute knowledge. Finally, we bridge the above two traits by an unlikelihood objective for prompt-tuning. Extensive experimental results show that DisCup can achieve a new state-of-the-art control performance while maintaining an efficient and high-quality text generation, only relying on around 10 virtual tokens.
Anthology ID:
2022.emnlp-main.223
Volume:
Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing
Month:
December
Year:
2022
Address:
Abu Dhabi, United Arab Emirates
Editors:
Yoav Goldberg, Zornitsa Kozareva, Yue Zhang
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
3392–3406
Language:
URL:
https://aclanthology.org/2022.emnlp-main.223
DOI:
10.18653/v1/2022.emnlp-main.223
Bibkey:
Cite (ACL):
Hanqing Zhang and Dawei Song. 2022. DisCup: Discriminator Cooperative Unlikelihood Prompt-tuning for Controllable Text Generation. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pages 3392–3406, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.
Cite (Informal):
DisCup: Discriminator Cooperative Unlikelihood Prompt-tuning for Controllable Text Generation (Zhang & Song, EMNLP 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.emnlp-main.223.pdf