Guiding Generative Language Models for Data Augmentation in Few-Shot Text Classification

TL;DR

This paper explores how guiding GPT-2 with domain expertise and seed selection strategies can enhance data augmentation for few-shot text classification, leading to improved model performance especially in specialized domains.

Contribution

It demonstrates that fine-tuning GPT-2 with selected seed examples and domain expert guidance improves data augmentation quality and classification accuracy in few-shot NLP tasks.

Findings

Fine-tuning GPT-2 improves classification performance.

Seed selection strategies impact sample quality.

Expert-guided augmentation yields further gains.

Abstract

Data augmentation techniques are widely used for enhancing the performance of machine learning models by tackling class imbalance issues and data sparsity. State-of-the-art generative language models have been shown to provide significant gains across different NLP tasks. However, their applicability to data augmentation for text classification tasks in few-shot settings have not been fully explored, especially for specialised domains. In this paper, we leverage GPT-2 (Radford A et al, 2019) for generating artificial training instances in order to improve classification performance. Our aim is to analyse the impact the selection process of seed training examples have over the quality of GPT-generated samples and consequently the classifier performance. We perform experiments with several seed selection strategies that, among others, exploit class hierarchical structures and domain expert selection. Our results show that fine-tuning GPT-2 in a handful of label instances leads to consistent classification improvements and outperform competitive baselines. Finally, we show that guiding this process through domain expert selection can lead to further improvements, which opens up interesting research avenues for combining generative models and active learning.