A Lightweight Neural Model for Biomedical Entity Linking - Equipe Data, Intelligence and Graphs Accéder directement au contenu
Pré-Publication, Document De Travail Année : 2020

A Lightweight Neural Model for Biomedical Entity Linking

Résumé

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. model is competitive with previous work on standard evaluation benchmarks.
Fichier principal
Vignette du fichier
8013.LihuC.pdf (298.59 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03086044 , version 1 (22-12-2020)
hal-03086044 , version 2 (25-05-2021)

Identifiants

  • HAL Id : hal-03086044 , version 1

Citer

Lihu Chen, Gaël Varoquaux, Fabian Suchanek. A Lightweight Neural Model for Biomedical Entity Linking. 2020. ⟨hal-03086044v1⟩
456 Consultations
268 Téléchargements

Partager

Gmail Facebook X LinkedIn More