Making Pre-trained Language Models Better Continual Few-Shot Relation Extractors

TL;DR

This paper introduces a contrastive prompt learning framework that enhances pre-trained language models for continual few-shot relation extraction, effectively reducing catastrophic forgetting and overfitting in low-resource settings.

Contribution

It proposes a novel contrastive prompt learning approach with memory augmentation, improving continual learning capabilities of language models for relation extraction.

Findings

Outperforms state-of-the-art methods significantly

Reduces catastrophic forgetting in continual learning

Mitigates overfitting in low-resource scenarios

Abstract

Continual Few-shot Relation Extraction (CFRE) is a practical problem that requires the model to continuously learn novel relations while avoiding forgetting old ones with few labeled training data. The primary challenges are catastrophic forgetting and overfitting. This paper harnesses prompt learning to explore the implicit capabilities of pre-trained language models to address the above two challenges, thereby making language models better continual few-shot relation extractors. Specifically, we propose a Contrastive Prompt Learning framework, which designs prompt representation to acquire more generalized knowledge that can be easily adapted to old and new categories, and margin-based contrastive learning to focus more on hard samples, therefore alleviating catastrophic forgetting and overfitting issues. To further remedy overfitting in low-resource scenarios, we introduce an effective memory augmentation strategy that employs well-crafted prompts to guide ChatGPT in generating diverse samples. Extensive experiments demonstrate that our method outperforms state-of-the-art methods by a large margin and significantly mitigates catastrophic forgetting and overfitting in low-resource scenarios.