EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Improving dictionary-based named entity recognition with deep learning

Katerina Nastou iD, Mikaela Koutrouli, Sampo Pyysalo, Lars Juhl Jensen

Bioinformatics · 2024

DOI: 10.1093/bioinformatics/btae402 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Bioinformatics, 2024. Verfasst von Katerina Nastou und 3 weiteren Autor:innen. Beteiligte Einrichtung: Novo Nordisk Foundation Center for Protein Research, Faculty of Health and Medical Sciences, University of Copenhagen, Blegdamsvej 3, Copenhagen, 220…. Hauptthemen laut MEDLINE: Deep Learning. Die Arbeit wurde bisher 6-mal zitiert (Crossref) und nennt 35 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Novo Nordisk Foundation, Academy of Finland, European Union's Horizon 2020.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Motivation Dictionary-based named entity recognition (NER) allows terms to be detected in a corpus and normalized to biomedical databases and ontologies. However, adaptation to different entity types requires new high-quality dictionaries and associated lists of blocked names for each type. The latter are so far created by identifying cases that cause many false positives through manual inspection of individual names, a process that scales poorly. Results In this work, we aim to improve block list s by automatically identifying names to block, based on the context in which they appear. By comparing results of three well-established biomedical NER methods, we generated a dataset of over 12.5 million text spans where the methods agree on the boundaries and type of entity tagged. These were used to generate positive and negative examples of contexts for four entity types (genes, diseases, species, and chemicals), which were used to train a Transformer-based model (BioBERT) to perform entity type classification. Application of the best model (F1-score = 96.7%) allowed us to generate a list of problematic names that should be blocked. Introducing this into our system doubled the size of the previous list of corpus-wide blocked names. In addition, we generated a document-specific list that allows ambiguous names to be blocked in specific documents. These changes boosted text mining precision by ∼5.5% on average, and over 8.5% for chemical and 7.5% for gene names, positively affecting several biological databases utilizing this NER system, like the STRING database, with only a minor drop in recall (0.6%). Availability and implementation All resources are available through Zenodo https://doi.org/10.5281/zenodo.11243139 and GitHub https://doi.org/10.5281/zenodo.10289360.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Deep LearningDatabases, FactualDictionaries as TopicComputational BiologyNatural Language ProcessingData Mining

Autor:innen und Institutionen

  • Novo Nordisk Foundation Center for Protein Research, Faculty of Health and Medical Sciences, University of Copenhagen, Blegdamsvej 3, Copenhagen, 2200, Denmark.
  • TurkuNLP Group, Department of Computing, University of Turku, Turku, 20014, Finland.

ORCID-Profile: Katerina Nastou

Förderung

  • Novo Nordisk Foundation
  • Academy of Finland
  • European Union's Horizon 2020
  • Marie Sklodowska-Curie
  • European Union’s Horizon 2020

Zitieren

APA

Nastou, K., Koutrouli, M., Pyysalo, S., & Jensen, L. J. (2024). Improving dictionary-based named entity recognition with deep learning. Bioinformatics. https://doi.org/10.1093/bioinformatics/btae402

Vancouver

Nastou K, Koutrouli M, Pyysalo S, Jensen LJ. Improving dictionary-based named entity recognition with deep learning. Bioinformatics. 2024. doi:10.1093/bioinformatics/btae402

BibTeX
@article{Nastou2024,
  author = {Nastou, Katerina and Koutrouli, Mikaela and Pyysalo, Sampo and Jensen, Lars Juhl},
  title = {Improving dictionary-based named entity recognition with deep learning},
  journal = {Bioinformatics},
  year = {2024},
  doi = {10.1093/bioinformatics/btae402}
}
Kostenlos starten →