Hyperbolic Representations for Prompt Learning

Nan Chen, Xiangdong Su, Feilong Bao


Abstract
Continuous prompt tuning has gained significant attention for its ability to train only continuous prompts while freezing the language model. This approach greatly reduces the training time and storage for downstream tasks. In this work, we delve into the hierarchical relationship between the prompts and downstream text inputs. In prompt learning, the prefix prompt acts as a module to guide the downstream language model, establishing a hierarchical relationship between the prefix prompt and subsequent inputs. Furthermore, we explore the benefits of leveraging hyperbolic space for modeling hierarchical structures. We project representations of pre-trained models from Euclidean space into hyperbolic space using the Poincaré disk which effectively captures the hierarchical relationship between the prompt and input text. The experiments on natural language understanding (NLU) tasks illustrate that hyperbolic space can model the hierarchical relationship between prompt and text input. We release our code at https://github.com/myaxxxxx/Hyperbolic-Prompt-Learning.
Anthology ID:
2024.lrec-main.744
Volume:
Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)
Month:
May
Year:
2024
Address:
Torino, Italia
Editors:
Nicoletta Calzolari, Min-Yen Kan, Veronique Hoste, Alessandro Lenci, Sakriani Sakti, Nianwen Xue
Venues:
LREC | COLING
SIG:
Publisher:
ELRA and ICCL
Note:
Pages:
8487–8492
Language:
URL:
https://aclanthology.org/2024.lrec-main.744
DOI:
Bibkey:
Cite (ACL):
Nan Chen, Xiangdong Su, and Feilong Bao. 2024. Hyperbolic Representations for Prompt Learning. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pages 8487–8492, Torino, Italia. ELRA and ICCL.
Cite (Informal):
Hyperbolic Representations for Prompt Learning (Chen et al., LREC-COLING 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.lrec-main.744.pdf
Optional supplementary material:
 2024.lrec-main.744.OptionalSupplementaryMaterial.pdf