A Lightweight Neural Model for Biomedical Entity Linking

Authors

  • Lihu Chen LTCI Télécom Paris Institut Polytechnique de Paris
  • Gaël Varoquaux Inria CEA Université Paris-Saclay
  • Fabian M. Suchanek LTCI Télécom Paris Institut Polytechnique de Paris

Keywords:

Information Extraction, Bioinformatics, Linked Open Data, Knowledge Graphs & KB Completio

Abstract

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.

Downloads

Published

2021-05-18

How to Cite

Chen, L., Varoquaux, G., & Suchanek, F. M. (2021). A Lightweight Neural Model for Biomedical Entity Linking. Proceedings of the AAAI Conference on Artificial Intelligence, 35(14), 12657-12665. Retrieved from https://ojs.aaai.org/index.php/AAAI/article/view/17499

Issue

Section

AAAI Technical Track on Speech and Natural Language Processing I