Knowledge-injected Prompt Learning for Chinese Biomedical Entity Normalization

TL;DR

This paper introduces a knowledge-injected prompt learning approach for Chinese biomedical entity normalization, effectively leveraging external medical knowledge to improve entity matching, especially in few-shot scenarios.

Contribution

The paper proposes a novel knowledge-injected prompt learning method that enhances Chinese BEN by encoding and integrating medical knowledge into the model, addressing data scarcity issues.

Findings

Outperforms baselines with 12.96% accuracy boost in few-shot scenarios

Achieves 0.94% higher accuracy in full-data scenarios

Demonstrates effectiveness in both few-shot and full-scale BEN tasks

Abstract

The Biomedical Entity Normalization (BEN) task aims to align raw, unstructured medical entities to standard entities, thus promoting data coherence and facilitating better downstream medical applications. Recently, prompt learning methods have shown promising results in this task. However, existing research falls short in tackling the more complex Chinese BEN task, especially in the few-shot scenario with limited medical data, and the vast potential of the external medical knowledge base has yet to be fully harnessed. To address these challenges, we propose a novel Knowledge-injected Prompt Learning (PL-Knowledge) method. Specifically, our approach consists of five stages: candidate entity matching, knowledge extraction, knowledge encoding, knowledge injection, and prediction output. By effectively encoding the knowledge items contained in medical entities and incorporating them into our tailor-made knowledge-injected templates, the additional knowledge enhances the model's ability to capture latent relationships between medical entities, thus achieving a better match with the standard entities. We extensively evaluate our model on a benchmark dataset in both few-shot and full-scale scenarios. Our method outperforms existing baselines, with an average accuracy boost of 12.96\% in few-shot and 0.94\% in full-data cases, showcasing its excellence in the BEN task.