Few-Shot Text Classification with Triplet Networks, Data Augmentation, and Curriculum Learning

By Jason Wei, Chengyu Huang, Soroush Vosoughi, Yu Cheng, Shiqi Xu. 2021

66 citations recorded by the source corpus.

Few-shot text classification is a fundamental NLP task in which a model aims to classify text into a large number of categories, given only a few training examples per category. This paper explores data augmentation—a technique particularly suitable for training with limited data—for this few-shot, highly-multiclass text classification setting. On four diverse text classification tasks, we find that common data augmentation techniques can improve the performance of triplet networks by up to 3.0% on average. To further boost performance, we present a simple training strategy called curriculum data augmentation, which leverages curriculum learning by first training on only original examples and then introducing augmented data as training progresses. We explore a two-stage and a gradual schedule, and find that, compared with standard single-stage training, curriculum data augmentation trains faster, improves performance, and remains robust to high amounts of noising from augmentation.

Subfields: Artificial Intelligence, Natural Language Processing, Meta & Continual Learning

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Natural Language Processing

Citations in the corpus

Text Data Augmentation for Deep Learning (2021, background): “Wei et al. [132] demonstrate the efficacy of gradually introducing augmented examples to original examples in the training of triplet networks for text classification.”