Abstract
Recent advances in prompt tuning have proven effective as a new language modeling paradigm for various natural language understanding tasks. However, it is challenging to adapt the soft prompt embeddings to different domains or generalize to low-data settings when learning soft prompts itself is unstable, task-specific, and bias-prone. This paper proposes a principled learning framework—soft prompt construction (SPC)—to facilitate learning domain-adaptable soft prompts. Derived from the SPC framework is a simple loss that can plug into various models and tuning approaches to improve their cross-domain performance. We show SPC can improve upon SOTA for contextual query rewriting, summarization, and paraphrase detection by up to 5%, 19%, and 16%, respectively.- Anthology ID:
- 2023.repl4nlp-1.10
- Volume:
- Proceedings of the 8th Workshop on Representation Learning for NLP (RepL4NLP 2023)
- Month:
- July
- Year:
- 2023
- Address:
- Toronto, Canada
- Editors:
- Burcu Can, Maximilian Mozes, Samuel Cahyawijaya, Naomi Saphra, Nora Kassner, Shauli Ravfogel, Abhilasha Ravichander, Chen Zhao, Isabelle Augenstein, Anna Rogers, Kyunghyun Cho, Edward Grefenstette, Lena Voita
- Venue:
- RepL4NLP
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 118–130
- Language:
- URL:
- https://aclanthology.org/2023.repl4nlp-1.10
- DOI:
- 10.18653/v1/2023.repl4nlp-1.10
- Cite (ACL):
- Wenbo Zhao, Arpit Gupta, Tagyoung Chung, and Jing Huang. 2023. SPC: Soft Prompt Construction for Cross Domain Generalization. In Proceedings of the 8th Workshop on Representation Learning for NLP (RepL4NLP 2023), pages 118–130, Toronto, Canada. Association for Computational Linguistics.
- Cite (Informal):
- SPC: Soft Prompt Construction for Cross Domain Generalization (Zhao et al., RepL4NLP 2023)
- PDF:
- https://preview.aclanthology.org/nschneid-patch-4/2023.repl4nlp-1.10.pdf