Improving Biomedical Entity Linking with Retrieval-enhanced Learning
Abstract
Biomedical entity linking (BioEL) has achieved remarkable progress with the help of pre-trained language models. However, existing BioEL methods usually struggle to handle rare and difficult entities due to long-tailed distribution. To address this limitation, we introduce a new scheme NN-BioEL, which provides a BioEL model with the ability to reference similar instances from the entire training corpus as clues for prediction, thus improving the generalization capabilities. Moreover, we design a contrastive learning objective with dynamic hard negative sampling (DHNS) that improves the quality of the retrieved neighbors during inference. Extensive experimental results show that NN-BioEL outperforms state-of-the-art baselines on several datasets.
Cite
@article{arxiv.2312.09806,
title = {Improving Biomedical Entity Linking with Retrieval-enhanced Learning},
author = {Zhenxi Lin and Ziheng Zhang and Xian Wu and Yefeng Zheng},
journal= {arXiv preprint arXiv:2312.09806},
year = {2023}
}
Comments
Accepted by ICASSP 2024