AMAL: Meta Knowledge-Driven Few-Shot Adapter Learning

S. K. Hong, Tae Young Jang


Abstract
NLP has advanced greatly together with the proliferation of Transformer-based pre-trained language models. To adapt to a downstream task, the pre-trained language models need to be fine-tuned with a sufficient supply of annotated examples. In recent years, Adapter-based fine-tuning methods have expanded the applicability of pre-trained language models by substantially lowering the required amount of annotated examples. However, existing Adapter-based methods still fail to yield meaningful results in the few-shot regime where only a few annotated examples are provided. In this study, we present a meta-learning-driven low-rank adapter pooling method, called AMAL, for leveraging pre-trained language models even with just a few data points. We evaluate our method on five text classification benchmark datasets. The results show that AMAL significantly outperforms previous few-shot learning methods and achieves a new state-of-the-art.
Anthology ID:
2022.emnlp-main.709
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:
10381–10389
Language:
URL:
https://aclanthology.org/2022.emnlp-main.709
DOI:
10.18653/v1/2022.emnlp-main.709
Bibkey:
Cite (ACL):
S. K. Hong and Tae Young Jang. 2022. AMAL: Meta Knowledge-Driven Few-Shot Adapter Learning. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pages 10381–10389, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.
Cite (Informal):
AMAL: Meta Knowledge-Driven Few-Shot Adapter Learning (Hong & Jang, EMNLP 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.emnlp-main.709.pdf