Self-Evolution Learning for Mixup: Enhance Data Augmentation on Few-Shot Text Classification Tasks

Haoqi Zheng, Qihuang Zhong, Liang Ding, Zhiliang Tian, Xin Niu, Changjian Wang, Dongsheng Li, Dacheng Tao


Abstract
Text classification tasks often encounter few-shot scenarios with limited labeled data, and addressing data scarcity is crucial. Data augmentation with mixup merges sample pairs to generate new pseudos, which can relieve the data deficiency issue in text classification. However, the quality of pseudo-samples generated by mixup exhibits significant variations. Most of the mixup methods fail to consider the varying degree of learning difficulty in different stages of training. And mixup generates new samples with one-hot labels, which encourages the model to produce a high prediction score for the correct class that is much larger than other classes, resulting in the model’s over-confidence. In this paper, we propose a self-evolution learning (SE) based mixup approach for data augmentation in text classification, which can generate more adaptive and model-friendly pseudo samples for the model training. SE caters to the growth of the model learning ability and adapts to the ability when generating training samples. To alleviate the model over-confidence, we introduce an instance-specific label smoothing regularization approach, which linearly interpolates the model’s output and one-hot labels of the original samples to generate new soft labels for label mixing up. Through experimental analysis, experiments show that our SE brings consistent and significant improvements upon different mixup methods. In-depth analyses demonstrate that SE enhances the model’s generalization ability.
Anthology ID:
2023.emnlp-main.555
Volume:
Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing
Month:
December
Year:
2023
Address:
Singapore
Editors:
Houda Bouamor, Juan Pino, Kalika Bali
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
8964–8974
Language:
URL:
https://aclanthology.org/2023.emnlp-main.555
DOI:
10.18653/v1/2023.emnlp-main.555
Bibkey:
Cite (ACL):
Haoqi Zheng, Qihuang Zhong, Liang Ding, Zhiliang Tian, Xin Niu, Changjian Wang, Dongsheng Li, and Dacheng Tao. 2023. Self-Evolution Learning for Mixup: Enhance Data Augmentation on Few-Shot Text Classification Tasks. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 8964–8974, Singapore. Association for Computational Linguistics.
Cite (Informal):
Self-Evolution Learning for Mixup: Enhance Data Augmentation on Few-Shot Text Classification Tasks (Zheng et al., EMNLP 2023)
Copy Citation:
PDF:
https://aclanthology.org/2023.emnlp-main.555.pdf
Video:
 https://aclanthology.org/2023.emnlp-main.555.mp4