Few-Shot, No Problem: Descriptive Continual Relation Extraction
Nguyen Xuan Thanh, Anh Duc Le, Quyen Tran, Thanh-Thien Le, Linh Ngo Van, Thien Huu Nguyen
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.
BibTeX
@article{Thanh_Duc Le_Tran_Le_Van_Nguyen_2025, title={Few-Shot, No Problem: Descriptive Continual Relation Extraction}, volume={39}, url={https://ojs.aaai.org/index.php/AAAI/article/view/34715}, DOI={10.1609/aaai.v39i24.34715}, abstractNote={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.}, number={24}, journal={Proceedings of the AAAI Conference on Artificial Intelligence}, author={Thanh, Nguyen Xuan and Duc Le, Anh and Tran, Quyen and Le, Thanh-Thien and Van, Linh Ngo and Nguyen, Thien Huu}, year={2025}, month={Apr.}, pages={25282-25290} }