EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

BELHD: improving biomedical entity linking with homonym disambiguation

Samuele Garda iD, Ulf Leser

Bioinformatics · 2024

DOI: 10.1093/bioinformatics/btae474 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Bioinformatics, 2024. Verfasst von Samuele Garda und 1 weiteren Autor:innen. Beteiligte Einrichtung: Computer Science, Humboldt-Universität zu Berlin, Berlin 12489, Germany. Hauptthemen laut MEDLINE: Natural Language Processing. Die Arbeit wurde bisher 5-mal zitiert (Crossref) und nennt 33 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Deutsche Forschungsgemeinschaft.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Motivation Biomedical entity linking (BEL) is the task of grounding entity mentions to a given knowledge base (KB). Recently, neural name-based methods, system identifying the most appropriate name in the KB for a given mention using neural network (either via dense retrieval or autoregressive modeling), achieved remarkable results for the task, without requiring manual tuning or definition of domain/entity-specific rules. However, as name-based methods directly return KB names, they cannot cope with homonyms, i.e. different KB entities sharing the exact same name. This significantly affects their performance for KBs where homonyms account for a large amount of entity mentions (e.g. UMLS and NCBI Gene). Results We present BELHD (Biomedical Entity Linking with Homonym Disambiguation), a new name-based method that copes with this challenge. BELHD builds upon the BioSyn model with two crucial extensions. First, it performs pre-processing of the KB, during which it expands homonyms with a specifically constructed disambiguating string, thus enforcing unique linking decisions. Second, it introduces candidate sharing, a novel strategy that strengthens the overall training signal by including similar mentions from the same document as positive or negative examples, according to their corresponding KB identifier. Experiments with 10 corpora and 5 entity types show that BELHD improves upon current neural state-of-the-art approaches, achieving the best results in 6 out of 10 corpora with an average improvement of 4.55pp recall@1. Furthermore, the KB preprocessing is orthogonal to the prediction model and thus can also improve other neural methods, which we exemplify for GenBioEL, a generative name-based BEL approach. Availability and implementation The code to reproduce our experiments can be found at: https://github.com/sg-wbi/belhd.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Natural Language ProcessingNeural Networks, ComputerKnowledge BasesAlgorithmsUnified Medical Language SystemHumansComputational Biology

Autor:innen und Institutionen

  • Computer Science, Humboldt-Universität zu Berlin, Berlin 12489, Germany.

ORCID-Profile: Samuele Garda

Förderung

  • Deutsche Forschungsgemeinschaft

Zitieren

APA

Garda, S., & Leser, U. (2024). BELHD: improving biomedical entity linking with homonym disambiguation. Bioinformatics. https://doi.org/10.1093/bioinformatics/btae474

Vancouver

Garda S, Leser U. BELHD: improving biomedical entity linking with homonym disambiguation. Bioinformatics. 2024. doi:10.1093/bioinformatics/btae474

BibTeX
@article{Garda2024,
  author = {Garda, Samuele and Leser, Ulf},
  title = {BELHD: improving biomedical entity linking with homonym disambiguation},
  journal = {Bioinformatics},
  year = {2024},
  doi = {10.1093/bioinformatics/btae474}
}
Kostenlos starten →