A Lightweight Neural Model for Biomedical Entity Linking
This work provides a more accessible and resource-efficient solution for biomedical entity linking, which is beneficial for researchers and practitioners with limited computational resources.
This paper addresses the challenge of biomedical entity linking, where mentions of diseases and drugs need to be mapped to standard entities in a knowledge base. The authors propose a lightweight neural model that significantly reduces the number of parameters and computational resources compared to BERT-based methods, while maintaining competitive performance on standard benchmarks.
Biomedical entity linking aims to map biomedical mentions, such as diseases and drugs, to standard entities in a given knowledge base. The specific challenge in this context is that the same biomedical entity can have a wide range of names, including synonyms, morphological variations, and names with different word orderings. Recently, BERT-based methods have advanced the state-of-the-art by allowing for rich representations of word sequences. However, they often have hundreds of millions of parameters and require heavy computing resources, which limits their applications in resource-limited scenarios. Here, we propose a lightweight neural method for biomedical entity linking, which needs just a fraction of the parameters of a BERT model and much less computing resources. Our method uses a simple alignment layer with attention mechanisms to capture the variations between mention and entity names. Yet, we show that our model is competitive with previous work on standard evaluation benchmarks.