Few-Shot, No Problem: Descriptive Continual Relation Extraction

TL;DR

This paper introduces a retrieval-based approach for few-shot continual relation extraction, leveraging large language models and bi-encoder training to improve knowledge retention and adapt to evolving relationships.

Contribution

It presents a novel retrieval-based framework using relation descriptions and bi-encoder training to enhance few-shot continual relation extraction performance.

Findings

Significantly outperforms existing methods on multiple datasets.

Effectively mitigates catastrophic forgetting in sequential tasks.

Enhances relation representation learning with description-based retrieval.

Abstract

Few-shot Continual Relation Extraction is a crucial challenge for enabling AI systems to identify and adapt to evolving relationships in dynamic real-world domains. Traditional memory-based approaches often overfit to limited samples, failing to reinforce old knowledge, with the scarcity of data in few-shot scenarios further exacerbating these issues by hindering effective data augmentation in the latent space. In this paper, we propose a novel retrieval-based solution, starting with a large language model to generate descriptions for each relation. From these descriptions, we introduce a bi-encoder retrieval training paradigm to enrich both sample and class representation learning. Leveraging these enhanced representations, we design a retrieval-based prediction method where each sample "retrieves" the best fitting relation via a reciprocal rank fusion score that integrates both relation description vectors and class prototypes. Extensive experiments on multiple datasets demonstrate that our method significantly advances the state-of-the-art by maintaining robust performance across sequential tasks, effectively addressing catastrophic forgetting.