Papers by Tae Young Jang
LEA: Meta Knowledge-Driven Self-Attentive Document Embedding for Few-Shot Text Classification (2022.naacl-main)
Copied to clipboard
| Challenge: | Existing few-shot text classification methods often lack labeled data in real-world tasks. |
| Approach: | They propose a meta-learning method that encodes how to attend for given tasks . they evaluate the method on five benchmark datasets and show it is competitive . |
| Outcome: | The proposed method performs better on five benchmark datasets than previous methods on labeled data. |
AMAL: Meta Knowledge-Driven Few-Shot Adapter Learning (2022.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods for fine-tuning pre-trained language models fail to yield meaningful results in the few-shot regime. |
| Approach: | They propose a meta-learning-driven low-rank adapter pooling method for leveraging pre-trained language models even with just a few data points. |
| Outcome: | The proposed method outperforms previous few-shot learning methods on five text classification benchmark datasets. |