Proceedings

MEDA: Meta-Learning with Data Augmentation for Few-Shot Text Classification

Pengfei Sun, Yawen Ouyang, Wenming Zhang, Xin-yu Dai

Download BibTeX Cite

Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence. Main Track. Pages 3929-3935.

https://doi.org/10.24963/ijcai.2021/541

Keywords

  • Natural Language Processing: Text Classification
  • Natural Language Processing: Natural Language Processing

Abstract

Meta-learning has recently emerged as a promising technique to address the challenge of few-shot learning. However, standard meta-learning methods mainly focus on visual tasks, which makes it hard for them to deal with diverse text data directly. In this paper, we introduce a novel framework for few-shot text classification, which is named as MEta-learning with Data Augmentation (MEDA). MEDA is composed of two modules, a ball generator and a meta-learner, which are learned jointly. The ball generator is to increase the number of shots per class by generating more samples, so that meta-learner can be trained with both original and augmented samples. It is worth noting that ball generator is agnostic to the choice of the meta-learning methods. Experiment results show that on both datasets, MEDA outperforms existing state-of-the-art methods and significantly improves the performance of meta-learning on few-shot text classification.

Pengfei Sun, Yawen Ouyang, Wenming Zhang, and Xin-Yu Dai. 2021. MEDA: Meta-Learning with Data Augmentation for Few-Shot Text Classification. In Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence, IJCAI-21. IJCAI, 3929–3935. https://doi.org/10.24963/ijcai.2021/541
Welcome Future Conferences AI Journal Division IJCAI Proceedings About IJCAI IJCAI Awards