PDAMeta: Meta-Learning Framework with Progressive Data Augmentation for Few-Shot Text Classification

Xurui Li, Kaisong Song, Tianqianjin Lin, Yangyang Kang, Fubang Zhao, Changlong Sun, Xiaozhong Liu


Abstract
Recently, we have witnessed the breakthroughs of meta-learning for few-shot learning scenario. Data augmentation is essential for meta-learning, particularly in situations where data is extremely scarce. However, existing text data augmentation methods can not ensure the diversity and quality of the generated data, which leads to sub-optimal performance. Inspired by the recent success of large language models (LLMs) which demonstrate improved language comprehension abilities, we propose a Meta-learning framework with Progressive Data Augmentation (PDAMeta) for few-shot text classification, which contains a two-stage data augmentation strategy. First, the prompt-based data augmentation enriches the diversity of the training instances from a global perspective. Second, the attention-based data augmentation further improves the data quality from a local perspective. Last, we propose a dual-stream contrastive meta-learning strategy to learn discriminative text representations from both original and augmented instances. Extensive experiments conducted on four public few-shot text classification datasets show that PDAMeta significantly outperforms several state-of-the-art models and shows better robustness.
Anthology ID:
2024.lrec-main.1109
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:
12668–12678
Language:
URL:
https://aclanthology.org/2024.lrec-main.1109
DOI:
Bibkey:
Cite (ACL):
Xurui Li, Kaisong Song, Tianqianjin Lin, Yangyang Kang, Fubang Zhao, Changlong Sun, and Xiaozhong Liu. 2024. PDAMeta: Meta-Learning Framework with Progressive Data Augmentation for Few-Shot Text Classification. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pages 12668–12678, Torino, Italia. ELRA and ICCL.
Cite (Informal):
PDAMeta: Meta-Learning Framework with Progressive Data Augmentation for Few-Shot Text Classification (Li et al., LREC-COLING 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.lrec-main.1109.pdf
Optional supplementary material:
 2024.lrec-main.1109.OptionalSupplementaryMaterial.zip