Enhancing Effectiveness and Robustness in a Low-Resource Regime via Decision-Boundary-aware Data Augmentation

Kyohoon Jin, Junho Lee, Juhwan Choi, Sangmin Song, Youngbin Kim


Abstract
Efforts to leverage deep learning models in low-resource regimes have led to numerous augmentation studies. However, the direct application of methods, such as mixup and cutout, is limited due to the discrete characteristics of the textual data. While methods using pre trained language models have exhibited good efficiency, they require additional considerations for robustness. Inspired by recent studies on decision boundaries, this paper proposes a decision-boundary-aware data augmentation strategy to enhance robustness using pretrained language models. The proposed technique first focuses on shifting the latent features closer to the decision boundary, followed by reconstruction to generate an ambiguous version with a soft label. Additionally, mid-K sampling is suggested to enhance the diversity of the generated sentences. This paper demonstrates the performance of the proposed augmentation strategy compared to other methods through extensive experiments. Furthermore, the ablation study demonstrates the effect of soft labels and mid-K sampling and the extensibility of the method with curriculum data augmentation.
Anthology ID:
2024.lrec-main.525
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:
5930–5943
Language:
URL:
https://aclanthology.org/2024.lrec-main.525
DOI:
Bibkey:
Cite (ACL):
Kyohoon Jin, Junho Lee, Juhwan Choi, Sangmin Song, and Youngbin Kim. 2024. Enhancing Effectiveness and Robustness in a Low-Resource Regime via Decision-Boundary-aware Data Augmentation. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pages 5930–5943, Torino, Italia. ELRA and ICCL.
Cite (Informal):
Enhancing Effectiveness and Robustness in a Low-Resource Regime via Decision-Boundary-aware Data Augmentation (Jin et al., LREC-COLING 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.lrec-main.525.pdf