Few-Shot, No Problem: Descriptive Continual Relation Extraction

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Thanh, Nguyen Xuan, Le, Anh Duc, Tran, Quyen, Le, Thanh-Thien, Van, Linh Ngo, Nguyen, Thien Huu
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910849967325184
author Thanh, Nguyen Xuan
Le, Anh Duc
Tran, Quyen
Le, Thanh-Thien
Van, Linh Ngo
Nguyen, Thien Huu
author_facet Thanh, Nguyen Xuan
Le, Anh Duc
Tran, Quyen
Le, Thanh-Thien
Van, Linh Ngo
Nguyen, Thien Huu
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2502_20596
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Few-Shot, No Problem: Descriptive Continual Relation Extraction
Thanh, Nguyen Xuan
Le, Anh Duc
Tran, Quyen
Le, Thanh-Thien
Van, Linh Ngo
Nguyen, Thien Huu
Computation and Language
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.
title Few-Shot, No Problem: Descriptive Continual Relation Extraction
topic Computation and Language
url https://arxiv.org/abs/2502.20596