IDPG: An Instance-Dependent Prompt Generation Method
Zhuofeng Wu, Sinong Wang, Jiatao Gu, Rui Hou, Yuxiao Dong, V.G.Vinod Vydiswaran, Hao Ma
Abstract
Prompt tuning is a new, efficient NLP transfer learning paradigm that adds a task-specific prompt in each input instance during the model training stage. It freezes the pre-trained language model and only optimizes a few task-specific prompts. In this paper, we propose a conditional prompt generation method to generate prompts for each input instance, referred to as the Instance-Dependent Prompt Generation (IDPG). Unlike traditional prompt tuning methods that use a fixed prompt, IDPG introduces a lightweight and trainable component to generate prompts based on each input sentence. Extensive experiments on ten natural language understanding (NLU) tasks show that the proposed strategy consistently outperforms various prompt tuning baselines and is on par with other efficient transfer learning methods such as Compacter while tuning far fewer model parameters.- Anthology ID:
- 2022.naacl-main.403
- Volume:
- Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
- Month:
- July
- Year:
- 2022
- Address:
- Seattle, United States
- Editors:
- Marine Carpuat, Marie-Catherine de Marneffe, Ivan Vladimir Meza Ruiz
- Venue:
- NAACL
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 5507–5521
- Language:
- URL:
- https://aclanthology.org/2022.naacl-main.403
- DOI:
- 10.18653/v1/2022.naacl-main.403
- Cite (ACL):
- Zhuofeng Wu, Sinong Wang, Jiatao Gu, Rui Hou, Yuxiao Dong, V.G.Vinod Vydiswaran, and Hao Ma. 2022. IDPG: An Instance-Dependent Prompt Generation Method. In Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 5507–5521, Seattle, United States. Association for Computational Linguistics.
- Cite (Informal):
- IDPG: An Instance-Dependent Prompt Generation Method (Wu et al., NAACL 2022)
- PDF:
- https://preview.aclanthology.org/dois-2013-emnlp/2022.naacl-main.403.pdf
- Data
- GLUE, MPQA Opinion Corpus, QNLI