---
title: "MEDA: Meta-Learning with Data Augmentation for Few-Shot Text Classification"
authors:
  - "Pengfei Sun"
  - "Yawen Ouyang"
  - "Wenming Zhang"
  - "Xin-yu Dai"
doi: "10.24963/ijcai.2021/541"
url: "https://ijcai.org/proceedings/2021/541"
pdf: "https://ijcai.org/proceedings/2021/0541.pdf"
venue: "Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence"
year: 2021
pages: "3929-3935"
track: "Main Track"
keywords:
  - "Natural Language Processing: Text Classification"
  - "Natural Language Processing: Natural Language Processing"
---

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

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

*Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence*, pages 3929-3935. DOI: [10.24963/ijcai.2021/541](https://doi.org/10.24963/ijcai.2021/541)

## 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.